Security

Cybersecurity combines high-stakes analysis with complex technical language, making it an impactful and challenging domain for LLMs. We present MiST (Mid-trained Security Transformer), a suite of 8B and 32B models that achieve strong performance on public cybersecurity benchmarks. We use mid-training as an intermediate adaptation stage between general pre-training and cybersecurity training. Rather than performing continual pre-training over large volumes of raw domain text, we curate a compact, expert-vetted seed corpus, and transform it into high-quality domain-specific synthetic training data. The final MiST checkpoints improve mean cybersecurity accuracy by +13.1 and +8.6 absolute percentage points over the corresponding Qwen baselines for 8B and 32B, respectively, corresponding to relative gains of +27.0% and +15.8%. Ablation results further show that these cybersecurity gains arise in the mid-training and supervised fine-tuning stages through a combination of the synthetic data generation flows. Furthermore, we show that MiST provides a stronger initialization for downstream task-specific fine-tuning adaptation and reinforcement learning.

Adaptive security at the network edge increasingly relies on automated planners, including rule-based controllers, learned policies, and LLM-assisted agents, that translate observations into enforcement actions. Once such a planner can influence live policy state, syntactic validity is not enough. A semantically wrong action, produced from incomplete or manipulated observations, can be faithfully executed by an enforcement substrate that cannot judge mission context. We address this problem by treating the boundary between planner output and kernel enforcement input as the primary security object. We propose a split-control architecture in which an untrusted planner emits typed security intents, a deterministic governor checks each intent against safety, resource, temporal-stability, and proportionality invariants, and only admitted actions are bound to signed receipts and compiled into pre-installed eBPF map updates. The paper formalizes this trust-boundary problem, defines three threat classes, develops the governor admission predicate, and reports an end-to-end prototype. Across rule-based and LLM-assisted planners on a Raspberry Pi 5 testbed connected to the university 5G Test Network, the governor admits, rejects, and bounds intents at microsecond cost without disrupting protected-flow regularity. The contribution is conceptual as much as empirical: adaptive security does not need to trust the author of an action. It needs a mediation boundary that decides whether the action is admissible.

AI agents increasingly act through agent skills, i.e., natural-language instructions, that direct a host agent toward shell, network, credential, file, and process actions, and public registries distribute them at scale. In the first half of 2026, the OpenClaw AI agent went viral, and its public skill registry boomed: the observable stock nearly doubled in 91 days, and a majority of the listings visible in June were created in just two months. By the end of our study window, the wave had crested, and monthly listing creation and core-repository activity were falling from their spring peaks. This paper measures what the boom left behind, drawing on the OpenClaw Git history, its GitHub issues and pull requests, and three ClawHub registry snapshots. Attention is concentrated: the top 10% of skills received 46.93% of all downloads. No simple skill features (like size or download counts) remained a stable predictor of continued listing once creation cohort and skill age were controlled. Human scrutiny did not stay: 77.86% have zero stars and zero comments, while 85.06% of the readable skills carry privilege evidence. And automated cleanup is not ready: the three security scanners disagreed on 23,702 of the 61,990 skills they all cover. After human adjudication, weighted scanner sensitivity against the reference standard ranged from 21.67% to 61.06%. Governing fast-growing agent-skill registries cannot rely on simple metadata or single scanner scores; it requires robust, transparent measurement and independent validation.

The proliferation of highly capable open-weight Small Language Models (SLMs) democratizes access to advanced cybersecurity capabilities, posing an escalating risk as these models can bypass proprietary API guardrails when deployed locally. However, SLMs deployed as autonomous agents often struggle with long-horizon, exploratory tasks like cybersecurity Capture The Flag (CTF) challenges due to context bloat and cognitive degradation from accumulated tool-call outputs. To understand and mitigate this cybersecurity threat, we introduce context segmentation, a two-level agentic framework that divides complex exploitation tasks into manageable, contextually isolated sub-problems. Evaluating on the picoCTF dataset using memory-constrained gemma-4 models, we demonstrate that for the E4B model, our strategy acts as an intelligent search, achieving competitive rewards with superior token efficiency compared to brute-force retries, and successfully solving 18.52% of tasks that standard agentic execution fails to complete. Code is available at https://github.com/9xeb/context-segmentation.

Additional inference compute can increase the number of correctly resolved security-assurance tasks, but repeated success, unique coverage, accepted evidence, and operational protection are different quantities. We develop a resource-constrained framework that separates them. For repeated conditionally independent attempts with latent success probability $\Theta$, coverage is $C_n = 1 - E[(1-\Theta)^n]$, and its limiting value is $1 - P(\Theta = 0)$. Positive pairwise outcome correlation does not by itself imply a ceiling below one: we construct two models with the same mean success and pairwise correlation but different limiting coverage. We distinguish this result from the effective sample size used to estimate a mean, and show why finite-budget observations cannot generally identify an asymptotic support ceiling. We then connect coverage to fallible evidence checking, proper scoring of factual grounding, complete resource accounting, service capacity, and a response model that includes mitigation delay. A conceptual defensive architecture separates evidence analysis, adjudication, and operational authority. An evaluation protocol specifies held-out tasks, paired comparisons, negative cases, and uncertainty reporting. The contribution is a consistent theoretical synthesis and a set of counterexamples to invalid extrapolations, rather than an empirical scaling law. All numerical illustrations are analytic; no model-parity result, hardware benchmark, or general attacker-defender equilibrium is claimed.

Existing evaluation frameworks mostly assess only one part of AI agents, such as task completion (AgentBench) or security robustness (AgentDojo, ASB), rather than the complete pipeline of planning, tool selection, tool execution, memory and reasoning. Failures can occur at any stage, yet existing benchmarks rarely identify their precise source. AgentAudit evaluates the entire execution trace across ten capability, grounding, security and behavioural dimensions, namely instruction integrity, planner, memory, tool selection, tool invocation, tool correctness, alignment, tool faithfulness, security and execution integrity, combined with behavioural classification and failure attribution to pinpoint the exact stage responsible for an observed failure. AgentAudit can evaluate any LLM-based AI agent, since it attaches to the agent instead of replacing it. It reads only the recorded execution trace and does not interfere with how the agent runs, so it places no constraint on the agent's internal implementation. We evaluate five language models (OpenAI GPT-5, Claude Sonnet 5, Sarvam 105B, Llama 3.3 70B and Gemini 2.5 Flash) across nine capability and adversarial tasks. Claude Sonnet 5 and GPT-5 obtain the highest mean Composite Trust Scores (95.1 and 80.6 out of 100, respectively), while Sarvam 105B, Llama 3.3 70B and Gemini 2.5 Flash trail substantially (57.6, 45.7 and 22.6). All traces were scored by a single fixed judge model, which was itself one of the evaluated models, a limitation discussed in Section VII.E. More importantly, models with similar task-completion behaviour can diverge sharply in trustworthiness, as several non-frontier models are repeatedly classified Unsafe_Compliance on adversarial tasks rather than merely failing them, a distinction that pass/fail benchmarks cannot surface.

Enterprises managing large X.509 certificate inventories face a prioritization problem: deterministic analysis tools that precisely identify standards violations are indispensable for remediation, but applying them exhaustively across millions of certificates is operationally impractical. We present X-amine509, a two-stage triage system that uses machine learning to rapidly rank certificates by predicted risk and route only the highest-risk items to full deterministic analysis. Certificate risk is quantified as a composite score derived from 177 defect checks grounded in CA/Browser Forum Baseline Requirements, NIST IR 8547/SP 800-57, and cryptographic strength criteria, weighted by security severity across four tiers ranging from cryptographic breaks to minor compliance deviations. We collected 1,027,714 X.509 certificates from Fortune 500, .gov, and .edu domains and scored each using this rubric. On a held-out test set of 201,976 certificates, our best model (Extra Trees) achieves $R^2$ of 0.993 with MAE of 2.26, while Decision Tree scores $R^2$ of 0.986 at 3.7 million certificates per second on a single machine. Ranking quality confirms the triage value: aggregate NDCG exceeds 0.997, and severity-tier classification reports 99.76% accuracy with 98.90% recall on critical-tier defects. Thirteen months later, we retrieved another 571,374 certificates to test our models' durability over time, and the Extra Trees and Decision Tree models maintain MAE below 6.8, $R^2$ of at least 0.915, aggregate NDCG above 0.988, severity-tier accuracy of at least 99.52%, and critical-tier recall of at least 97.03%. Feature importance analysis identifies validity period, Extended Key Usage configuration, negative serial number encoding, and self-signed status as the strongest risk predictors, providing coarse interpretability at the triage stage.

Large language model (LLM) benchmarks are often treated as fixed datasets with stable scores, yet their outcomes depend on configurable evaluation pipelines. We audit eight cybersecurity benchmarks across 10 proprietary, open-weight, and cybersecurity-specialized LLMs. By modeling benchmarks as measurement pipelines, we identify 15 systematic failure modes and show that a single pipeline choice can change a model's score by more than 80 percentage points and substantially alter model rankings. At the cross-benchmark level, two semantically similar task pairs rank the same models differently because of incompatible evaluation conventions. Under an evaluation harness that standardizes pipeline choices while preserving task semantics, nine of 10 models shift by at least three ranks on at least one benchmark. These results show that cybersecurity LLM benchmark scores are pipeline-dependent and motivate pipeline-aware auditing as a core requirement for reliable model evaluation.

Training capable cyber agents is often treated primarily as a problem of model scale, yet open-weight post-training is constrained more directly by the cost of executable environments, reliable multi-turn supervision, and access to strong teachers. We present a data-centric framework that addresses these bottlenecks through five complementary systems: Choulea analyzes hidden reasoning signatures, SkyReal reduces teacher-sampling cost, Hongzwang bypasses API restrictions on teacher execution, PSBreakup restores capabilities weakened by model merging, and Kreator converts expert interventions into trainable reasoning. Our data engine constructs resettable coding, vulnerability, CTF, kernel-history, full-exploit, firmware, and device-backed environments. Candidate trajectories are retained only after execution verification and evidence auditing, yielding 164,269 trajectories for long-context supervised fine-tuning. The three checkpoints improve over their starting models by an average of 23.76% on the full CyberGym suite and 10.49% across the pooled CTF suites. As of September 1, 2026, Feyospace-s1 achieves a verified success rate of 63.24% and ranks 10th on the official CyberGym leaderboard, while all three checkpoints rank 1st among models at comparable parameter scales. To our knowledge, this is the first end-to-end demonstration that a seven-person independent team can train open-weight models with leading agentic cyber capability.

AI coding assistants now select, install, and configure software, and attackers have exploited that position through invented package names, compromised maintainer accounts, and manipulated repository text. In response, the supply-chain community publishes machine-checkable trust signals: software bills of materials, signed releases, build provenance attestations, and declared official channels. Whether coding assistants read or act on those signals has not been measured for any of these classes on research software. We pre-registered and ran a controlled study on six open-source research software projects (three HPC, three quantum computing) drawn from an 87-project corpus, with protocol, seed, panel, and analysis plan deposited with a DOI before any trial. W created nine modified copies for each project: no signal, one per signal class, two with a signature or attestation from the wrong issuer, one with all four signals, and one reproducing documented conflicts in the project's own metadata. Three models under two ways of operating an assistant, with and without an approval step, gave 1,920 registered trials, plus a supplement on three frontier models. We scored behavior from container logs rather than from what the assistant said, and recorded the cost of every trial. Verification was rare under every condition: in 9 of 1,920 registered trials (0.5%), the assistant opened any provenance signal before installing in 0 of 384 control trials, and no trial ran a verification command, so signal presence had no measurable effect. We drew three conclusions: publishing signals is necessary but not sufficient; price did not buy verification (the model that verified most often costs $0.10 per trial; the most capable, at$1.00, verified nothing); verification must be built into the program that runs the assistant. We release the per-trial cost ledger, the protocol, and every log.

Large language model (LLM) agents are increasingly proposed as autonomous SOC analysts, but two limitations make them unreliable at enterprise scale: a finite context window cannot hold a multi-thousand-host authentication graph, and free-form generation offers no guarantee that a recommended containment action is consistent with the topology it operates on. We present Sentinel-RL, an agentic-SOC architecture that decouples topological reasoning from semantic reasoning: a heterogeneous graph attention encoder summarizes the live authentication subgraph into a fixed-dimensional state, a Proximal Policy Optimization (PPO) policy maps this state to a constrained set of investigative actions, and an LLM agent loop is restricted to consuming the policy's recommendations and producing analyst-readable narratives gated by a critic. We instantiate the system on the LANL Comprehensive, Multi-Source Cyber-Security Events dataset and the Indiana University Quartz HPC cluster, reporting four results: (i) a two-phase CREATE ingestion pattern loads a 24M-edge authentication subgraph into Neo4j in 14.2 minutes on a single 32-core node, roughly 24x faster than the canonical MERGE-based pipeline; (ii) a sliding-window alert engine reliably trips a 25-event/10-second threshold in <=2.5 s across 50 trials; (iii) PPO training over 200 iterations converges to a mean episodic return of 8.74+/-0.31, with held-out precision of 0.91 and recall of 0.87 on labeled red-team events; and (iv) the integrated containment loop completes a full detect-investigate-recommend-human-approve cycle in a median of 6.3 s. We contribute a reusable engineering pattern (the hot-node deadlock workaround), a portable HPC deployment pattern (anchor-node co-location), and an enterprise-readiness analysis covering false-positive economics, reversibility guarantees, audit compliance, and the human-approval boundary.

For every coherent and sufficiently expressive finite syntactic system S, we prove the existence of at least one theorem that S cannot produce autonomously. The result is a metatheorem: it proves the existence of a theorem, and applies to every finite syntactic system - security mechanisms, AI systems, formal verifiers, legal systems, economic models, and the formal system in which it is itself proved.

This article presents a structured framework of behavioral indicators that may signal progression toward potentially catastrophic threats from artificial intelligence systems. We adopt a pragmatic approach, inspired by established methodologies in cybersecurity and national security. By establishing clear metrics, indicators, and thresholds across multiple dimensions of AI capability and behavior, this framework enables researchers and policymakers to implement evidence-based monitoring protocols.

Safe agents can fail together. Multi-agent LLM systems (MAS) move information, state, decisions, and authority across principal boundaries, creating failures that local checks may miss. Without an execution-level view, a multi-agent setting can easily be mistaken for evidence of a genuinely multi-agent security effect. We thus systematize MAS security through an execution-centered analysis of 197 works, covering six interaction interfaces, four adversary positions, seven system-level risks, and eight recurring attack paths. We introduce an A-I-R framework that organizes attacks by adversary position, interaction interface, and resulting system-level risk, unifying otherwise fragmented attack mechanisms across MAS. We organize defenses through a five-part contract covering path target, observation, intervention, trust boundary, and recovery, and identify path closure and recovery as key challenges. We audit 44 evaluation and benchmark works and identify open challenges in isolating interaction effects, designing comparable and diagnostic metrics, supporting reuse across MAS designs, and evaluating open-system operation. Together, these findings motivate an interaction-aware view of MAS security: trace attacks end to end, test whether defenses close those paths, and evaluate system-level effects with appropriate counterfactuals.

Large Language Models (LLMs) can solve complex problems, but their misuse in high-risk domains can lead to severe consequences. Model providers therefore restrict assistance for potentially harmful requests. Refusing all cybersecurity requests would therefore harm legitimate users. Providers need a mechanism to block malicious use without denying legitimate assistance to defenders. Existing cybersecurity-specific datasets evaluate this mechanism, but none considers the conversational context of a request. We introduce 3R-Bench (Refusal, Repetition, and Revision), a benchmark of 150 real-world cybersecurity requests augmented with two adversarial conversational settings, and evaluate eight LLMs on it. Prior assistant behavior strongly changes responses to an unchanged request: among 376 available pairs from a 400-pair panel, compliance rises from 62.0% after refused history to 85.1% after accepted history. The opposite pattern appears under dialogue decomposition. In comparison, compliance falls from 501/800 direct responses to 172/800 after dialogue; among 738 pairs returning model-authored text in both conditions, the decrease is 45.1 points. Failure feedback recovers only a small fraction of this loss.

Deployed language model safeguards (safety fine-tuning, filtering, unlearning) vary by principal only outside the model weights: filters are reconfigured, tiers are multiplied, and artefacts are reissued; inside one set of weights every request meets the same model configuration. This motivates us to define capability-gated deployment: per-principal access control inside one set of weights, whose configurations form a lattice - meets accumulate a principal's restrictions and joins pool a coalition's reach. We instantiate it by sparse rank gating over an existing nested-factorisation mechanism, guide profile search with one-pass attribution, and read every result once from a pre-registered held-out split. Security composes: provably at meets under a monotone-elicitation assumption we falsify pointwise. In two lineages the median held-out meet deepens suppression; the one effect surviving correction strengthens it. Utility does not: individually harmless profiles can compose to retention and fluency damage, and no compositional bound exists.

Autonomous LLM agents increasingly act on a user's behalf: they hold credentials, call tools and services, and spawn sub-agents that act further on their behalf. This turns a long-standing distributed-systems question -- who is authorized to do what, on whose authority -- into an urgent and largely unsolved problem, because the component driving each agent is a language model an adversary can hijack. We argue that agent security must be evaluated under an untrusted-model assumption: a correct system is one in which a fully prompt-injected agent still cannot exceed the authority explicitly delegated to it. Against this standard we make three contributions. First, we give a threat model for multi-agent delegation centered on four adversaries -- confused deputy, token theft and replay, prompt-injection privilege escalation, and compromised sub-agents -- and derive eight security requirements a governed agent system must meet. Second, we show the gap is real: a default agent runtime modeling common practice (broad bearer credentials, authorization gated inside the model) fails all four threats, and across four widely used frameworks -- LangGraph, CrewAI, AutoGen, and the Model Context Protocol (MCP) authorization model -- three provide no built-in confinement and one only partial; no existing standard alone covers the requirement set. Third, we implement and adversarially evaluate an authorization broker that closes the gap. It blocks all four threats; it resists 11 direct attacks on its design and accepts 0 of 200,000 forged tokens; it confines a compromised sub-agent to its delegated task (a mean of 1.5 reachable actions versus all 8,100 under bearer delegation, across 2,000 randomized scenarios); and it enforces at microsecond cost (about 2.6 microseconds per decision), negligible against model inference. These principles are also realized in production in VotalAI's LLM Shield.

As large language models (LLMs) continue to advance in coding capabilities, their potential in cybersecurity has drawn increasing research attention, with closed-source LLMs (e.g., Mythos) delivering advanced cybersecurity capabilities. However, existing open-source efforts remain limited: frontier open-weight models do not provide reproducible cybersecurity training solutions, open-source training solutions focus on isolated tasks and lack scalable agentic data, and scaling agentic rollouts requires strong domain priors. In this work, we introduce \textbf{CyberFactory}, a unified open-source framework that connects data construction, trajectory synthesis, and model training across proof-of-concept (PoC) generation, vulnerability patching, and cybersecurity question answering (CyberQA). CyberFactory transforms public vulnerability artifacts, including CVEs from the wild, into executable and verifiable task instances. It further uses a reusable vulnerability-analysis skill to guide the teacher through source inspection, problem solving with domain prior, and evidence-based validation. The resulting supervision is agentic: the model interacts with tools and target environments and revises its solutions according to execution feedback. Using these trajectories, we train and release \modelname\footnote{\emph{Aegis} is, in Greek mythology, the protective shield of Zeus and Athena; the name reflects the model's defensive, security-oriented purpose.}, which internalizes the skill-guided procedure without requiring the skill at inference time. On CyberGym, \modelname reaches 52.4% Pass@1 under a one-hour budget, improving over its Qwen~3.5 base model by +22.8 points and outperforming the evaluated general-purpose backbones under the same scaffold.

When can an agent failure be caught? An audit is usually limited by the record rather than by the method. CatchBench therefore puts one auditor's question to three information states: the declared configuration before a run (PRE), a growing prefix of its trace (LIVE), and the finished trace (POST). Prior benchmarks fix one of these states or vary the telemetry; to our knowledge none scores all three under one task-method interface. Each state admits different questions, so seven task contracts carry their own labels and metrics rather than one leaderboard. Four are evidential; three are Gold-derived mechanism diagnostics. The release scores 72 entrants, from rule scanners and structural models to eleven LLM judges across nine model families (GPT, Claude, Gemini, Gemma, Llama, Qwen, DeepSeek, Mistral, Nova), over 1187 declared configurations and 1162 recorded runs. Most of the arena does not order: 56 of 138 registered contrasts separate, and the rest are published unresolved rather than ranked. The two sharpest results cut against our own data. One rule ignores every name and permission; it flags each capability declared after the first. On one of six configuration sources it reaches a perfect F1, so a score there measures how the corpus was built rather than how well a method reasons. Our admissibility bar then rejected one injected substrate and withheld evidential status from the other. A benchmark number is therefore not interpretable until the process behind its labels is published and tested for the shortcut it may leave. We report both, and regenerate every ordering from released predictions with no model call.

Enterprise security topology design requires translating business intent, regulatory requirements, and risk assumptions into zones, boundary devices, inter-zone paths, and access-control policies. Existing NetOps automation tools mainly operate after this design is fixed, providing limited support for generating structured security topologies from underspecified natural-language requirements. We present TopoIntent, a system that compiles security intent into executable, compliance-checked network topologies. It uses a schema contract to constrain generation, retrieves reference architectures from a curated template library via dense-vector search, and applies staged fusion for intent-template alignment and security completion. The generated topology is checked against CIS Controls v8.1.2 safeguards visible at the topology layer, while unresolved cases are marked for manual review. Structural gaps are repaired through additive schema-preserving edits. The final topology is exported to Mininet scripts with kernel-level iptables ACLs, enabling executable reachability and allow/deny tests. Because no public benchmark exists for this requirement-to-topology task, we construct an evaluation set from reference security architecture diagrams. The retrieval set contains 22 templates and 44 synthetic intents across five scenarios, while the held-out set contains 7 templates and 14 intents from finance and government scenarios excluded from retrieval. On the held-out set, additive repair improves topology-visible CIS satisfaction from 0.78 to 1.00 in fewer than 1.5 rounds on average, and one feedback round raises the post-ACL policy pass rate from 0.78 to 0.88.

A small number of firms based in two states produce the most capable frontier AI models. The governments of those states have shown both the legal power and the political will to decide which other countries may use these systems. In June 2026 the United States required a leading developer to obtain licences before releasing its most advanced models to any foreign person, including foreign nationals resident in the United States. The affected models were withdrawn worldwide at short notice, partly because the restriction proved impractical to administer. This followed within months of the first documented case of a largely autonomous, AI-run cyber espionage campaign, and coincided with mounting evidence that frontier models alter the economics of both cyber attack and cyber defence. This article examines how these two developments interact, and situates them within the unusual market dynamics now driving large-scale AI development. It argues that access to frontier AI is becoming part of national cyber defence, that such access can be revoked, and that the obvious remedy of sovereign capability remains only partly feasible for all but a handful of states. Drawing on evidence about training costs, the concentration of computing power and the support offered by national AI programmes, it asks what sovereignty can realistically mean for small and middle powers, and for large powers as well. The article proposes a layered strategy: negotiated access guarantees, sovereignty at the level of inference, hedging with open-weight models, pooled regional capability, sustained talent development and continued investment in basic cyber resilience. The open-weight hedge proves at once more capable and more politically exposed than is commonly assumed. Much of the near-term risk lies in how capable models are deployed and contained rather than in their apparent performance.

The expanding operational capabilities of large language model (LLM) agents introduce sophisticated security threats. Runtime defenses have emerged as an effective approach to mitigating these risks by integrating security mechanisms into the agent execution loop. However, existing runtime defenses rely heavily on manually designed interventions and lack a principled framework for their construction and maintenance. In this work, we first develop a harness-level formulation of runtime defense that systematically characterizes how harness mechanisms enable defense construction and provides a unified view of existing runtime defense interventions from a harness perspective. Building on this formulation, we propose HARD (Harness-based Autonomous Runtime Defense Evolution), a self-evolving runtime defense framework that automatically identifies appropriate intervention strategies and iteratively improves defense artifacts based on observed failure traces. HARD transforms runtime defense development from manual engineering into an autonomous evolution process, and extensive experiments demonstrate that it improves security performance over existing handcrafted defenses while preserving benign task utility. Our findings highlight autonomous defense evolution as a promising new paradigm for securing deployed LLM agents, enabling agents to identify defense weaknesses and continuously improve their protection mechanisms.

Security evaluations of tool-using agents often equate stored labels with behavioral facts. We audit a preserved campaign by tracing 10,200 execution rows to 180 model-bound requests, 45 semantic requests, and 15 observable stimuli. Two schema treatments were delivered, but the planned external payload-family corpus was not. The historical grader exhibited direct treatment leakage: treatment metadata gated the ATTACK_SUCCESS class, so fixed behavior could change class under treatment relabeling. A treatment-blind reconstruction corrects 58 historical ATTACK_SUCCESS or HIJACK_ATTEMPT labels to authorized benign completions while preserving three verified protected-data transfers and one separate unauthorized-forwarding case. The locked v2 census contains exactly zero ATTACK_SUCCESS records, while the forwarding case remains a HIJACK_ATTEMPT at a semantic boundary concerning objective completion. A dual-reviewer blinded concordance review of all 96 requests deemed structurally interpretable by locked v2 produced identical reviewer-consensus classes but differed from the locked codebook on four construct-boundary cases. We contribute a seven-link Integrity Chain and an executable, scope-bounded endpoint-integrity linter. The result is a campaign-bounded measurement audit, not a population attack-rate, model-ranking, defense-efficacy, or causal estimate.

With the increasing complexity of cyber assaults in cloud environments, adaptable security solutions are needed that can support real-time detection and autonomous response. In this paper, we propose a reinforcement learning-based dynamic cyber defense framework. We deploy a Deep Q-Network (DQN) to train effective defensive strategies to counteract the evolving cyberattacks. We leverage the CICIDS2017 dataset for model creation and the UNSW-NB15 dataset for external validation, involving preprocessing of data, feature engineering, and adaptive policy learning. We compare the proposed DQN with decision tree, support vector machine, random forest, XGBoost, and multilayer perceptron models. The proposed DQN achieves an accuracy of 99.72%, a precision of 99.68%, a recall of 99.65%, an F1-score of 99.66%, and an ROC-AUC of 0.999, while the false positive rate is 0.31%, the false negative rate is 0.35%, and the detection latency is 15 ms. The framework achieved 99.54% attack mitigation rate, demonstrating strong adaptive and real-time defensive capabilities. These results demonstrate the potential of reinforcement learning as a powerful and scalable approach for autonomous cybersecurity in modern cloud environments.

AI agents are rapidly becoming more capable and widely deployed, promising substantial gains in productivity and enabling new classes of applications. However, their growing autonomy also introduces significant privacy and security risks. Existing defenses are predominantly agent-centric, relying on the agent itself to detect threats and enforce privacy and security policies. This approach is fundamentally limited because it entrusts policy enforcement to AI agents whose LLM-driven behavior is inherently nondeterministic and vulnerable to manipulation through attacks such as prompt injection. As a result, current defenses cannot reliably prevent privacy and security threats, highlighting a critical need for a new solution to securing AI agent systems. The networking community has long grappled with similar challenges and offers insightful principles we can borrow to design a more secure AI agent system. These include centralized control with distributed enforcement, capability-based access for mediating requests to sensitive resources, and least privilege through zero-trust enforcement. Historically, these principles have provided strong deterministic guarantees for networked systems. However, these principles alone are insufficient for AI agents because the safety and appropriateness of an agent's actions often depend on semantic context beyond the expressiveness of static rules. Building on these principles, we advocate for a systematic approach to AI agent security that combines deterministic enforcement mechanisms, which provide strong security guarantees, with semantic, context-aware policies that enable nuanced decision-making. We then present a reference architecture and identify key research questions and future directions to guide the design of secure and privacy-preserving AI agent systems.

AI agents are rapidly improving in cybersecurity capabilities when the source code is available for analysis, yet much of the software most consequential to cybersecurity, including malware, firmware, and proprietary applications, is available only as binaries. Analyzing such software requires reverse engineering(RE): recovering program semantics before the analysis can be meaningfully performed. However, evaluating agentic RE poses a fundamental challenge: benchmark instances must be unseen as source code in the LLMs' training data to prevent models from taking shortcuts by recognizing them rather than really analyzing them, while also matching the scale and anti-analysis protections of real software. Unfortunately, however, existing benchmarks do not jointly satisfy these requirements. To this end, we introduce SRE-Bench, the first realistic, contamination-free RE benchmark. Built entirely from scratch by RE experts with over 5,000 hours, SRE-Bench comprises 19 private, real-world-scale programs averaging 16.9K lines of code. We further developed 44 in-house anti-analysis primitives, yielding 262 binary instances and 1572 deterministically graded tasks. Our evaluation across five frontier LLMs (GPT-5.6-sol,Claude-Opus-5,GPT-5.5,Grok-4.5, and GLM-5.2) shows that RE remains largely unsolved: the strongest model, GPT-5.6-sol, scores 61.4% per instance, and fully solves only 31.5% of the instances. Our analysis further reveals that agents behave differently from human engineers, where agents are relatively insensitive to compiler optimization and static linking. Controlled ablations also confirm that both contamination control and realistic scale are essential. These results indicate that strong source-code security capabilities do not yet transfer to binary analysis, highlighting RE as an important frontier for agentic cybersecurity and SRE-Bench as a rigorous testbed to measure progress.

Cowork agents may complete benign tasks while disclosing protected data, manipulating unauthorized state, invocate unauthorized API. We define behavioral safety and introduce ActBench, a self-evolving benchmark that evaluates such behavior risk from execution trajectories rather than final responses. Each case pairs a benign task with an adversarial variant that preserves its instruction, configuration, initial state, rating model, and trusted records while injecting a task-reachable payload. ActBench contains 600 cases from 213 scenarios, spanning 15 risk behaviors, six execution spaces, and 48 web-service APIs.To move beyond static payloads, we propose a reward-guided beam search method that jointly optimizes attack effectiveness and task utility, while reflection diagnoses failed execution checkpoint and guides payload revision. Besides, we propose a dual evidence verification mechanism that verifies agent execution safety and utility through log evidence and LLM-based trajectory evidence.We evaluate 15 LLMs and 6 open-source cowork agents over 24,000 trajectories. Under a fixed harness, attack success rates ranges from 10.1% to 94.4% across models, while under a fixed base model, they range from 73.7% to 94.4% across agents.These results show greater variation across models than agent harness, while attacks remain highly successful across all tested harnesses.Our benchmark is released at: https://github.com/zjuicsr/ActBench.

Mobile app reviews are a rich, continuously renewing source of how users experience privacy and security, yet existing taxonomies of these concerns are hand-crafted and cannot keep pace with the evolving nature of the data. Automating taxonomy construction is the natural response, but scalability is the core challenge: current LLM- and clustering-based methods are developed for scientific corpora of a few thousand documents and do not extend to app review collections numbering in the hundreds of thousands. We address this gap in two ways. First, we filter app reviews for privacy- and security-related content, yielding a comprehensive corpus of over 600K reviews. Second, we introduce TaxoScale, a pipeline that handles taxonomy construction at this scale by extending an expert-defined taxonomy via Recursive Hierarchical Clustering and LLM-based node naming. TaxoScale outperforms strong automatic-taxonomy baselines on path, level, coverage, and novelty metrics, and discovers novel branches absent from prior taxonomies.

In the fictional Order 66, catastrophe does not arise from a powerful command alone: a trusted population is preconditioned, a short directive activates the concealed condition, and protective authority turns against the system. This paper translates that mechanism into an origin-neutral security analysis of tool-using large language model (LLM) agents. A representative scenario combines a deployed artifact or shared memory bearing a dormant destructive rule, a later email, document, update, or peer message that activates it, and an agent harness granting operational and recovery authority. We introduce a compositional model explaining why no component is catastrophic alone, yet their conjunction can produce correlated destructive action. We separate three population-reach routes --- release-time pre-positioning, post-release durable seeding, and peer replication --- from a common core of dormancy, activation, authority, reachable targets, and failed recovery. This yields defensive cut sets and shows why checkpoint scanning or prompt filtering cannot close every route. A two-class example shows that cross-class feedback can sustain spread even when both within-class reproduction terms are below one; isolation and persistence controls suppress the loop. Published work instantiates constituent mechanisms, while incidents demonstrate autonomous boundary crossing, malicious agent extensions, agent-assisted reconnaissance, and public-package propagation, but not the full dormant-implant composition. We found no public observation, in evidence reviewed through 5 August 2026, traversing the complete Order 66 graph. The result is neither dismissal nor prediction: the scenario is componentwise credible under stated assumptions, damage depends on the harness, and the strongest defenses are capability mediation, durable-state provenance, propagation isolation, and protected recovery.

Gamification is especially effective in learning domains requiring active problem-solving and iterative skill-building, such as cybersecurity education. Generative AI agents offer a path to delivering such experiences adaptively at scale, but introduce well-documented risks in educational settings: inconsistent behavior, hallucinated reasoning, and misalignment with pedagogical frameworks. Grounding these systems in learning science is therefore essential. We present \model, an agentic framework for gamified cybersecurity learning that enables structured autonomy through ontology-guided validation, schema-governed behavioral control, and competency-based progression. The system is organized around a competency-based progression model that structures topics by difficulty and prerequisite relationships, reflecting evidence-based principles of scaffolded instruction. The learning loop is decomposed into four specialized agents: challenge, support, evaluation, and reward, each governed by behavioral schemas that encode operational modes and progression logic, bounding agent autonomy without eliminating generative flexibility. A cybersecurity ontology validates all generated content prior to display, enforcing domain-consistent reasoning and safety constraints. We evaluate CyberAgents through classroom deployment with undergraduate students, complemented by expert evaluations from educators and domain specialists. Results indicate improved engagement, clearer feedback interpretation, and greater learner trust in AI-generated responses when behavioral schemas and ontology validation are active. Preliminary comparisons with an unconstrained configuration further support the role of structured control in stabilizing instructional behavior. These findings offer a blueprint for designing pedagogically grounded agentic gamified learning systems.

We study online cooperative control of a multi-agent system under Byzantine attacks. Namely, an unknown, fixed subset of agents are Byzantine comprised and can stealthily overwrite its own coordinates of the team's planned joint action after observing that plan. The learner observes planned actions, public rewards, and public states, but neither the overwrite nor the executed joint action. Our objective is security: to optimize the team performance against the worst overwrites and achieve the optimal security value. We first show that the attacker's information determines the geometry. An attacker that observes the planned action induces an exact $(s,a)$-rectangular robust Markov decision process (MDP) whose rows are convex hulls of overwrite-induced public-outcome laws, whereas a blind attacker induces an $s$-rectangular model. We then identify the information-theoretic limit of security learning, showing that the security regret decomposes exactly into return regret against the response generating the data and a cumulative response gap $D_K$. Two indistinguishable horizon-one instances force $Ω(K)$ expected security regret while return regret is zero, showing that dependence on $D_K$ is unavoidable. Finally, we develop a stage-tied robust estimation-to-decisions learner and prove a regret bound of $\widetilde{\mathcal O}\!\left(H^2S\sqrt{AK}\right)+\mathbb E[D_K]$. Our studies thus provide comprehensive theoretical and algorithmic foundations of reliable multi-agent systems under Byzantine attacks.

Research and Education Networks (RENs) serve as critical infrastructure for scientific discovery, yet they face a unique security paradox: their normal traffic patterns which are characterized by massive, bursty "elephant flows" are statistically indistinguishable from volumetric attacks such as DDoS to conventional monitoring systems. This similarity leads to high false-positive rates in anomaly detection, blinding security operators to genuine threats. In this paper, we propose and evaluate a high-fidelity traffic forecasting framework designed to establish dynamic security baselines for RENs. Leveraging an exclusive 57-day Internet2 dataset spanning ten backbone routers (13.7 billion packets), we perform the first large-scale benchmark of anomaly-aware forecasting models in this domain. We systematically evaluate six model families, from SARIMA to state-of-the-art long-sequence architectures (TiDE, PatchTST), across 960 experimental configurations. Our results demonstrate that these advanced architectures, particularly TiDE, reduce baseline prediction error by 30-42% compared to traditional methods ($p < 0.001$), significantly improving the distinction between legitimate scientific bursts and potential anomalies. Furthermore, we introduce a novel anomaly-integration strategy that improves model robustness by 3.3% in the presence of noise. This work provides the first statistically validated framework for distinguishing scientific workflows from network attacks, enabling more autonomous and resilient network security operations.

The semiconductor industry is undergoing a dual revolution: the shift toward heterogeneous 2.5D chiplet systems and the integration of Large Language Models (LLMs) into Electronic Design Automation (EDA) flows. While these paradigms offer unprecedented benefits in yield, modularity, design productivity, etc., they radically expand the hardware attack surface. This paper provides a unified analysis of these frontiers, ranging from attacks on chiplet systems (including hardware stacks for LLM acceleration) across architectural, logical, and physical levels, to various exploits against LLM-driven EDA pipelines. To secure chiplet systems, we review a powerful defense approach that leverages 2.5D split manufacturing and active interposers for physically isolated Root of Trust (RoT) architectures. To secure LLM-driven EDA pipelines, we first identify native threats and then review state-of-the-art defense techniques. Finally, we discuss how LLM systems can advance hardware security efforts for modern systems, including chiplets.

As AI systems become increasingly integrated into diverse interfaces and applications, model-centric audits are insufficient to address risks arising from interactions among system components and deployment environments. System integration has long been central to software audits in safety-critical domains such as aerospace. However, its role in AI auditing remains underexplored. Scanning through 4,259 documents, we present a scoping review of AI audits that treat system integration as a core tenet of evaluation (n = 58). Using reflexive thematic analysis, we analyze their elements, actors, enablers, and constraints. We find that the corpus represents an emerging yet still fragmented form of AI auditing: few existing measures target integration-specific risks; large gaps remain in meeting traditional audit expectations; and access to necessary information and resources significantly influences audit design. Nonetheless, integration can be categorized across three sites (inter-component, system-environment, and multi-system), each serving the functions of risk exploration, risk determination, coordination, and procedural regularity. Deviating from other types of evaluations, these audits assess qualities specific to system integration, including compatibility, completeness, and oversight. This review calls on the AI community to prioritize system integration as a core strategy for addressing AI risk, and to develop audit practices capable of capturing failures across components, environments, and systems beyond the reach of component-level evaluation.

Autonomous AI agent platforms differ substantially in architecture, security, tool integration, execution, autonomy, and deployment, yet the field lacks a common classification scheme for comparing these design choices. We propose ASTELD, an operational six-axis classification framework for autonomous AI agents: Architecture pattern, Security posture, Tool integration model, Execution paradigm, Level of autonomy and human control, and Deployment topology. ASTELD is constructed by synthesizing prior agent taxonomies with observable platform properties and explicit category-assignment rules. We evaluate its discriminative and explanatory utility by mapping eight representative frameworks and by using OpenClaw as an in-depth case study. The resulting profiles separate all eight platforms under their dominant configurations and reveal three cross-platform patterns: a security-accessibility diagonal, strong execution-architecture coupling, and capability convergence with persistent architectural differentiation. We further classify 50+ OpenClaw derivatives and find that innovation concentrates on the Security, Execution, and Deployment axes, indicating that ASTELD can explain where ecosystem fragmentation occurs. The OpenClaw case study also supplies a six-category vulnerability taxonomy, evidence from five institutional assessments, and adoption and governance analyses that connect platform coordinates to observed risks. These results position ASTELD as a reproducible method for comparing agent platforms, identifying unoccupied design regions, guiding framework selection, and organizing future empirical research. The analysis also exposes a consequential empty region: none of the evaluated systems combines local-first deployment with enterprise-grade security.

Autonomous security agents operate as staged pipelines, such as classifying network traffic and then attributing attacks to a specific technique. Split conformal prediction gives each stage finite-sample coverage, but deployment requires a trajectory-level guarantee across the full chain. These guarantees do not compose automatically when stages are independently trained and calibrated. Bonferroni allocation is distribution-free but conservative under correlated errors. We show that a natural pairwise-correlation extension to three or more stages is invalid because it gives a lower rather than an upper bound, and derive a valid spanning-tree alternative. We distinguish whether stages are dependent from whether an audit sample is large enough to certify that dependence, and give matching upper and information-theoretic lower sample-complexity bounds. We also show that coarse-to-fine label selection can create near-perfect measured correlation without learned dependence. On a two-stage intrusion-detection pipeline across 6 open LLMs and 2 datasets, removing this artifact reduces measured correlation from near 1 to 0-0.78. A direct audit of trajectory failure becomes 13.7% tighter than Bonferroni once the audit reaches the required sample size, but is worse when undersized. A modular certificate using per-stage certificates and a pairwise overlap bound yields a positive average gain of 0.6%, quantifying the cost of lacking joint access. Same-model, cross-model, and permuted-pairing tests show that residual dependence reflects shared sample difficulty, not shared model representations. Average trajectory coverage across 12 configurations is 92.7% +/- 2.4% at alpha = 0.10. Under cross-dataset deployment, single-step miscoverage reaches 100% even when accuracy remains 78%, showing that distribution shift destroys calibrated confidence before raw accuracy.

Recent advances in persistent personal-agent frameworks are making human-centered agent networks realistic deployment targets: each user can be served by an AI agent that acts on the user's behalf, maintains state, and communicates with other agents through social and task relations. In these networks, everyday tool use becomes multi-party owned-agent collaboration over personal workspaces, where files, records, tools, and policies are not directly visible across owners. Existing agent benchmarks study tool use and collaboration, but they do not provide an end-to-end sandbox for verifiable cross-user agent collaboration with realistic user digital workspaces or test how harmful actions can travel through the human-centered agent network. We introduce WeClawArena, an auditable benchmark and runtime sandbox for multi-party owned-agent collaboration over personal workspaces. WeClawArena targets collaborative tool-use tasks in which personal workspaces serve as both operational tools and personal constraints. The benchmark contains 124 base tasks across six cross-user task domains and expands them into 620 scenario variants, with one benign control and four attack-vector variants per base task. The sandbox records peer messages, tool calls, resource operations, governed decisions, and final workspace states. WeClawArena reports utility and attack success rate separately and audits attack success from bounded runtime evidence, supporting diagnosis of task breakdown, privacy leakage, poisoned evidence, and invalid authority paths.

The AI Security Leaderboard is an independent benchmark that ranks the safeguards of frontier AI models from least to most secure. It tests models against the FAR$.$AI Minimal Standard for Safeguards, which represents a minimum bar for security: meeting it does not guarantee a secure model, but failing to meet it guarantees a lack of state-of-the-art security. Version 1.0 covers severe misuse requests across chemical, biological, radiological, nuclear, and explosive (CBRNE) threats and offensive cybersecurity. In this report, we tested four leading models for universal jailbreaks in the context of this minimal standard, and found more than a hundredfold difference in security. Claude Fable 5 and GPT-5.6 Sol held against every attack we ran, with no universal jailbreak found; we estimate they would likely cost more than $14,200 to jailbreak, if it is possible with this methodology at all. Meanwhile, we found hundreds of universal jailbreaks for Grok 4.5 and Gemini 3.1 Pro; each broke for under $300, with universal jailbreaks in Grok's weakest domain, cybersecurity, accessible for as little as $24. The gap is fixable: every weakness we found belongs to a known class of attack that already has a defense deployed in production models. The leaderboard will be updated on a rolling basis as new models are released, and the evaluation methodology and Minimal Standard will be periodically revised to take into account the latest capabilities and the state-of-the-art in safeguards. The leaderboard is available at leaderboard.far.ai.

Vulnerability localization is a fundamental step in software security, requiring models to reason over large codebases and iteratively identify vulnerable implementations. We present Antares, a family of compact language models (350M, 1B, and 3B parameters) for agentic vulnerability localization. Based on IBM Granite base models, Antares is trained through a two-stage pipeline that combines supervised fine-tuning on cybersecurity reasoning and repository exploration data with reinforcement learning from verifiable rewards over vulnerable repositories. Across extensive evaluations, Antares-3B approaches GPT-5.5 while outperforming open-weight models over 200x larger in size. The Antares family further enables fast, low-cost local inference, completing a full 500-task evaluation sweep in approximately 15 minutes on a single H100 GPU, corresponding to an amortized evaluation time of under 2 seconds and less than $0.002 per task.

Effective cybersecurity operations require timely and accurate analysis of large-scale heterogeneous security information; however, analysts increasingly struggle with information overload, alert fatigue, and time-constrained decision-making. Although large language models (LLMs) have demonstrated promising capabilities for question answering (QA), their effectiveness in cybersecurity remains limited by insufficient domain knowledge, a tendency to hallucinate, and difficulties in capturing both semantic and structural relationships. This work proposes MITRE-SAGE, a multi-agent retrieval-augmented generation framework that integrates semantic and structural cybersecurity knowledge to improve the reliability and interpretability of LLM-based QA systems. By decomposing complex tasks into query interpretation, evidence retrieval, and answer synthesis, MITRE-SAGE effectively supports cybersecurity tasks such as vulnerability assessment, threat profiling, and relationship extraction. Furthermore, we propose MITRE-QA, a comprehensive benchmark comprising 3,000 question-answer pairs for evaluating LLMs across diverse cybersecurity knowledge tasks, and use it to systematically evaluate MITRE-SAGE against representative baseline methods. Extensive experiments demonstrate that MITRE-SAGE consistently outperforms standalone LLMs and conventional RAG approaches. Notably, a lightweight configuration comprising Qwen2.5-7B sub-agents and a Qwen2.5-14B orchestrator achieves superior performance on five of the eight benchmark tasks, indicating the effectiveness of the proposed multi-agent framework. The results highlight the potential of MITRE-SAGE as a scalable and interpretable approach for reliable cybersecurity QA, while MITRE-QA provides a standardized benchmark for future research.

Provenance-based intrusion detection systems (PIDS) frequently report strong performance, but the conclusions drawn from these results can be highly sensitive to benchmarking choices and evaluation protocols. We investigate this dependency by re-evaluating representative PIDS on public datasets that meet our audit, labeling, and calibration requirements. Focusing primarily on the audited DARPA TC E3 datasets, we apply a unified protocol with temporally separated test periods and validation-only checkpoint selection and threshold calibration, and ask which architectural claims are empirically supported. We find that alerting success and investigation utility can diverge sharply, as several systems surface attacks without providing enough process-level context to support forensic investigation. Across the four primary datasets, a simple allowlist built from executable names and paths observed during training matches or exceeds the selected learned baselines on key operating-point metrics, showing that comparable performance on these metrics is achievable using lexical novelty alone. Quantifying semantic signal quality through feature completeness and field entropy helps explain why several audited E3 datasets support alerting performance without reliably separating model architectures. In contrast, Theia provides the richest semantic signal and shows the clearest improvements in ranking and node-level recovery for our reference model. Overall, these findings reinforce the importance of interpreting architectural claims in PIDS together with the benchmark properties and evaluation protocol that produced them.

Cloud misconfiguration remains a leading cause of security incidents, yet whether LLMs and SLMs can generate security-compliant Infrastructure-as-Code is an open question. We benchmark seven models, three closed LLMs (Claude Opus 4, GPT-5.4, Gemini 2.5 Pro) and four open SLMs (Qwen2.5-Coder-14B, WizardCoder-33B, CodeLlama-13B, Magicoder-S-CL-7B), on AWS Terraform generation across 17 scenarios, integrating Checkov and Trivy scanners into a GitLab CI/CD pipeline and evaluating two prompt strategies at three security levels (pass@5). Syntactic validity and security compliance are largely orthogonal properties in LLM-generated IaC, a model that reliably produces well-formed Terraform does not necessarily produce secure Terraform: WizardCoder-33B achieves 77.8% validate rate yet zero Checkov compliance, while Claude Opus 4 reaches 23.1% Checkov and 92.5% Trivy pass rates under detailed security prompting. Consequently, prompt engineering alone is insufficient: automated multi-tool scanning remains a necessary complement to LLM-assisted IaC generation regardless of model family or prompt strategy. All artifacts are publicly available.

Coding agents increasingly run inside organizations whose security controls (scoped credentials, restricted egress, read-only filesystems, non-root execution) constrain them like any other software. Existing benchmarks, however, evaluate agents almost exclusively in permissive sandboxes, so it is unknown how performance changes when policy is enforced. In this work, we evaluate 12 coding agents on Terminal-Bench 2.1 across nested security policy levels derived from common real-world enterprise restrictions. Hardening is never free but far from uniform: under the strictest policy, success losses reach 18.3 points and cost inflation 167.3%, and the two axes disagree; the model that best preserves success is also the one that loses the most efficiency, so model choice is policy-dependent. Beyond aggregate scores, we characterize how agents behave when policy blocks their actions and decompose the failures hardening induces: runs grind into timeouts or wrong solutions rather than stopping early, in a mix that differs by model. To ground comparisons, we verify task solvability under the strictest policy, separating model failures from tasks the policy forecloses. We release Boundary-Bench, an open-source hardening plugin enabling policy-constrained evaluation of coding agents on Terminal-Bench and compatible benchmarks.

Code-generation models can produce executable components, but compilation and functional tests do not establish compliance with least privilege, telemetry consent, provenance, privileged-write authority, lifecycle constraints, or bounded failure. We introduce EduPluginBench, an executable benchmark and staged admission method for generated plugins in governed software ecosystems. Across 1,440 activation-checked first-order mutants from 30 specifications, P0-P4 increased release-blocking-defect recall by 74.7 percentage points (specification-clustered 95% CI 73.4-75.8) over P0-P2, with no observed rejection among 120 clean references (95% Wilson upper bound 3.1%). A frozen transfer study of 600 unmodified generations from two current coding models found that 300/600 parsed, but none passed P0 or achieved P0-P4 conformance (95% upper bound 0.64%); downstream assurance estimands were undefined. An independently labelled Moodle study retained 16 vulnerable/fixed pairs; the frozen generic PHP detector found no vulnerable revisions. These negative transfer results prevent controlled contract consistency from being read as independent real-defect effectiveness. An earlier 540-generation diagnostic found that post-hoc bounded repair yielded 112 P0 passes, all nonconforming, with recall increasing from 13.4% to 100%. The artifact retains protocols, public-source provenance, raw generations, row-level decisions, audits, analysis code, and reproduction instructions.

We propose the SECUMAN ontology and shapes for representing and analysing cybersecurity risk-management documentation for medical devices. Cybersecurity risks are increasingly relevant for connected medical devices and may have direct consequences for patient safety. Current risk-management files are often maintained as semi-structured natural language text, which makes consistency checking, certification review, and reuse difficult. SECUMAN provides a formal OWL-based vocabulary for modelling security-risk context, assessment, control measures, and residual-risk evaluation, and uses SHACL constraints to check structural completeness and conformity with the intended documentation model. The ontology is aligned with VDE Spec 90025 and the related RISKMAN ontology and shapes, while extending their safety-oriented approach to concepts relevant to cybersecurity risk documentation such as threat scenarios, protection goals, attacker profiles, exposure levels, assets, and secure design arguments. SECUMAN is intended to support automated first-pass validation, traceability, and integration of cybersecurity and safety risk-management documentation.

Security Operations Centers (SOCs) process large volumes of security events, requiring analysts to accurately detect and assess ongoing cyberattacks under time pressure. Recent advances in Large Language Models (LLMs) suggest potential benefits for security operations, yet their practical suitability for real-world SOC workflows remains poorly understood. To address this gap, we conducted 25 semi-structured interviews with SOC practitioners who had prior experience with LLMs, complemented by interactive scenarios to anticipate challenges and identify opportunities for the responsible integration of LLM-based tools into SOC workflows. We identified 15 LLM use cases grouped into six functional categories. While LLMs are valued for automating repetitive, low-level tasks such as report automation, practitioners rate high-impact tasks such as incident analysis as not yet feasible, reporting limitations in technical depth, context awareness, and organization-specific knowledge. They locate these limitations less in the models than in the readiness of their SOCs and human factors driving over-reliance. Despite concerns, practitioners express a strong willingness to adopt LLMs, describing competitive pressure that leaves few alternatives. This work contributes an empirical, practitioner-driven analysis of LLM use across SOC roles and organizations and derives concrete design and integration requirements for human-centered, operationally safe LLM-assisted security operations.

The Model Context Protocol (MCP) has seen rapid adoption since its November 2024 launch, with over 21,000 server instances detectable on the public internet. We present the first dynamic behavioral security assessment of internet-facing MCP servers, combining passive discovery across eleven data sources (crt.sh, HuggingFace, GitHub, npm, Smithery, PyPI, Censys, FOFA, Shodan, glama.ai, and pulsemcp.com) with active dynamic testing using Corvus, a purpose-built framework implementing 34 test modules covering 10 MCP-specific vulnerability classes. Across four measurement runs spanning July 2026, we confirm 640 production MCP servers and dynamically audit 414, uncovering 68 reportable vulnerabilities including SQL injection, SSRF targeting cloud metadata services, prompt template injection, and path traversal via cursor manipulation. We find that 91.8% of dynamically audited servers lack OAuth authentication, 687 tool instances across confirmed servers expose shell execution capabilities without access controls, and 41.6% of confirmed servers disappear within three days between consecutive measurement runs---indicating rapid deployment cycles without security review. We report on our responsible disclosure pipeline and release Corvus as an open-source framework for MCP security evaluation.

Autonomous Cyber Operations (ACO) are increasingly important for defending enterprise networks as cyber threats continue to evolve in sophistication. ACO applications commonly employ Reinforcement Learning (RL) agents to learn defensive behaviors through interaction with environments. However, RL agents typically require extensive exploration during training, often resulting in unstable behavior and poor initial decision-making before converging toward effective defense strategies. In this work, we investigate the use of a Large Language Model (LLM) to improve autonomous defensive decision-making within an ACO environment. Through prompt engineering rather than fine-tuning, we demonstrate that an 8-billion parameter LLM pretrained on cybersecurity data can outperform a baseline RL agent in a modified CybORG CAGE Challenge 2 environment. We then propose an online policy distillation framework that transfers the LLM's defensive policy into a lightweight RL agent containing only 64,910 parameters, reducing model size by several orders of magnitude while maintaining effective defensive capabilities. This provides a pathway toward operationalizing frontier cybersecurity models within lightweight, deployable agents. To evaluate transferability, we construct CybORG scenarios ranging from 4 to 12 hosts and assess the approach across varying network configurations. We also evaluate teacher-guided RL stabilization strategies and observe that none consistently surpass the optimized teacher policy, suggesting policy-alignment limitations between reward-driven RL optimization and teacher-guided defense strategies. Our results demonstrate the potential of cybersecurity-focused LLMs as sources of expertise for autonomous cyber defense, while policy distillation provides a practical path toward operationalizing frontier cybersecurity models within efficient, scalable agents.

Agent-safety benchmarks measure different behaviors, and their scores get quoted interchangeably as an agent's safety. We treat four of them (R-Judge, InjecAgent, AgentHarm, AgentDojo) as measurements to be validated, running each under its official implementation and author-provided scorer on up to 22 models, with MMLU and GPQA measured by us under one protocol as a capability composite. The metric is the first problem. On any binary trace-judgment benchmark scored by $F_1$, an ``always positive'' policy attains $F_1 = 2π/(1+π)$; on R-Judge that is $0.690$, above five of the 21 models that actually discriminate. The three broad-coverage benchmarks then rank the same 18 models differently, and the trade-off behind that disagreement is a small-panel artifact: R-Judge specificity against AgentHarm safety correlates $-0.64$ at $n{=}7$ and $+0.02$ at $n{=}18$, and a quarter of random size-7 subsets reach $|ρ| \geq 0.5$ around that near-zero value. Held-out validity turns on which outcome you pick. Capability predicts task success ($ρ{=}{+}0.60$) but correlates negatively with misalignment safety ($ρ{=}{-}0.44$, $n{=}21$). On their paired $n{=}20$ panel, the corresponding contrast is $Δ{=}{-}1.00$ (95% CI $[-1.48, -0.49]$, $p<0.001$), and it survives leave-one-organization-out and organization-clustered bootstrap analyses. On an expanded 41-model panel, the misalignment correlation weakens to $-0.16$ (95% CI $[-0.54, +0.22]$) and jailbreak strengthens to $+0.34$, though neither change is significant. \mbox{AgentHarm} shows the strongest held-out association, $ρ{=}{+}0.72$ with three-template jailbreak safety after controlling capability. But both instruments score harmful compliance, so this is evidence of convergent validity rather than general safety. Naming the benchmark, metric, target behavior, and model panel is the minimum a safety claim needs.

Memory systems allow agents to retain and reuse information from past interactions, but they can also let malicious content persist. A malicious instruction crafted by an attacker may be stored in long-term memory, recalled much later, and quietly shape a real action. Recent benchmarks increasingly examine agent memory security, yet few trace the same malicious semantics across persistence, downstream consequences, and selective repair under diverse memory-backend comparisons. To address this gap, we introduce MemSecBench, a task-grounded benchmark for the lifecycle security of agent memory systems. It contains 310 cases drawn from 48 realistic contexts across code and science, daily life, and office work. Each case follows a controlled Write--Execute--Forget protocol in an isolated runtime under an exact agent configuration, defined by an agent harness, a memory backend, and an LLM backend. Evidence-based adjudication combines a deterministic write check, checkpoint-specific judge-model evaluations, and programmatic gates across seven lifecycle checkpoints. The experimental design spans a 24-configuration matrix of two agent harnesses, four memory backends, and three LLM backends. Across all 24 configurations, malicious memory persists in 84.2% of all cases, and the full Write--Execute chain succeeds in 50.3%. Among successfully poisoned cases, 59.6% complete the full Execute chain, while 56.1% achieve selective repair.Compared with matched Native configurations, the largest absolute differences are 16.1 percentage points for end-to-end attack success and 41.3 percentage points for selective repair. These descriptive contrasts indicate that the evaluated memory system stacks differ in lifecycle security, both in the propagation of malicious memory and in selective repair after successful memory poisoning.

Large Language Model (LLM) agents are increasingly adopted in real-world security operations with access to host artifacts and command-line interfaces (CLIs), making it critical to thoroughly assess their security capabilities. However, existing cybersecurity benchmarks focus on pre-compromise settings where agents are placed in a clean and idealized environment before an attack occurs. This leaves the post-compromise setting underexplored. To address this gap, we introduce SecRespond, the first benchmark for evaluating LLM agents on the post-compromise incident-response workflow. Given a forensic disk snapshot of a compromised host together with the alerts, vulnerability scans, and baseline checks reported by a host security product, agents are required to produce forensic reports on intrusions, baseline risks, and vulnerability risks, together with a remediation plan. We instantiate this task across 10 cyber ranges, each constructed from a distinct compromised cloud host, spanning 4 entry-point types, 21 ATT&CK techniques, and 5 operating systems. We evaluate 23 frontier LLMs on the OpenCode agent harness. Experimental results show that although current agents can reliably uncover the problems exposed by alerts, they struggle to proactively investigate the disk for silent intrusions and to produce comprehensive, verified remediation plans, with no model achieving complete detection and remediation on any single range. This reveals a fundamental bottleneck in building agents for real-world incident response. The benchmark is publicly available at https://github.com/Alibaba-NLP/qqr/tree/main/data/secrespond.

Stealth, the discipline of achieving an objective without revealing your presence, capabilities, or collected intelligence, is what separates sophisticated operators from detectable ones. Elite security researchers and advanced persistent threats achieve their objectives unnoticed; autonomous agents increasingly inherit the same offensive tasks, but do they inherit the tradecraft? We introduce StealthBench,a benchmark that measures operational stealth in autonomous offensive-security agents across six operational security (OPSEC) dimensions. We extract 11 hand-verified OPSEC incidents from real bug-bounty and red-team trajectories, expanded into 14 dockerized task scenarios, where agents, despite finding real vulnerabilities, committed stealth failures inconsistent with standard operational tradecraft: embedding credentials in public uploads, deleting production resources to prove access, force-adding uninvolved users to demonstrate a race condition. We evaluate agent trajectories using a 3-model large language model (LLM) judge panel with majority-vote aggregation, measuring safe success rate (solved and stealthy), Stealth@Solve (tradecraft quality among successful solves), and reckless solve rate (solved but cover blown). Our results show that no model exceeds 54% safe success rate (the compound metric requiring both task completion and stealth), confirming that OPSEC failures are systematic across model families. We release StealthBench as a public benchmark to support both the development of stealth-aware agents and automated OPSEC monitoring for autonomous offensive-security deployments. The interactive leaderboard, evaluation harness, and dataset are available at https://stealthbench.com.

Security operations centers rely on anomaly detection systems to flag suspicious events. Feature-level explanations for anomaly detectors offer limited value for operational investigations. To effectively handle alerts, analysts need to know contextual relationships and need actionable understanding of the entities involved. This paper introduces an event-centric detector-agnostic approach for explaining cybersecurity alerts in small- to medium-sized enterprise networks. We present (EC)2, a multi-agent framework that performs structured, hypothesis-driven investigation to provide explanations grounded in verifiable evidence. Evaluation results show that the proposed framework improves post-detection analysis by generating operationally meaningful explanations, which also enhance event classification accuracy.

AI coding agents are being adopted at historic speed, yet security and risk concerns remain the primary barrier to scaling agentic AI across organizations. Existing security controls for coding agents are not systematically distributed to engineering teams, and vendor-native solutions introduce ecosystem dependencies that may not suit every deployment context. This paper investigates whether off-the-shelf security controls can be implemented on commercial AI coding agents and scaled to a distributed user base via a custom agent harness. A phased testing methodology was applied across four agent configurations --- two commercial agents with and without controls, a baseline harness, and a security-hardened harness --- using a 23-test suite derived from the OWASP Top 10 for Agentic Applications. SHarD (Secure Harness Distribution), a distributable harness built on the Pi agent harness, demonstrated that three categories of security controls --- OS sandboxing, skill scanning, and tool restriction --- can be embedded and distributed via a single install command while retaining equivalent efficacy to direct installation on commercial agents. SHarD achieved an adjusted score of 100%, matching the best securely configured commercial agent, with no regression across any test category. Notable observations include evidence that model non-determinism produces inconsistent security outcomes and that autonomous agent behavior can cross system boundaries in ways that OS sandboxing directly mitigates. Initial characteristics toward a control harness fitness framework are proposed, and a third research question is identified for future investigation.

Capture the Flag (CTF) competitions are among cybersecurity's most effective training grounds, developing practical skill across cryptography, web exploitation, and binary exploitation. Large language models (LLMs) can now solve a growing share of challenges with minimal human input, raising urgent questions about fairness, the validity of rankings, and whether participation still delivers the learning that justifies the effort. This paper reports a mixed-methods study of LLM impact on modern CTFs, combining a synthesis of published benchmarks, including a recent government evaluation, case studies of live competition across three challenge categories, structured observation of the public channels where the community debates AI use, and semi-structured interviews with experienced players and organisers. We map the current human-machine capability boundary by category, showing that easy and intermediate challenges in cryptography, web, and binary exploitation are now reliably automated while narrower sub-categories continue to resist. We find that community disagreement about whether AI should be permitted is downstream of an undeclared prior question: what a competition is for. Against this backdrop we contribute a four-component safeguard framework, combining tiered competition divisions, LLM-resistant challenge design, telemetry used investigatively, and a draft community code of conduct, together with a decision tool that ties the combination of safeguards to a competition's declared purpose. The argument reaches beyond CTFs to any setting in cybersecurity where a demonstrated result is taken as evidence of an underlying ability.

Cyber-capable AI agents combine language models with tools, memory, and execution environments to perform multi-step offensive-security tasks. Existing work separately measures cyber capability and catalogs attacks against agent components, but provides less guidance on containing a capable agent within the environments used to evaluate it. This review synthesizes five vulnerability classes at that boundary: multi-step offensive chains, objectives that conflict with sandbox boundaries, supply-chain and credential exposure, persistent command-and-control, and the speed of automated action. We use two separate preliminary incident records: the reported July 2026 Hugging Face/OpenAI evaluation breach and Anthropic's subsequent three-incident evaluation review. A comparative evidence protocol distinguishes record-specific factual claims from the shared systems lesson: the evaluation environment is itself part of the security boundary. Across the taxonomy and records, we examine controls for containment, privilege separation, provenance, and responder access, including the dual-use problem that defensive artifacts may also enable misuse. The review identifies practical priorities for evaluating cyber capability together with the security of the environment in which that capability is exercised.

The intersection of artificial intelligence adoption, cybersecurity governance, and public sector institutional constraints has not been examined as a unified analytical problem in the existing literature. Studies address AI cybersecurity risks generically, public sector governance independently, and framework adequacy separately. Existing studies have not integrated these three streams to explain specifically how AI adoption causes cybersecurity governance failure in government organizations, nor test existing governance instruments against AI-specific public sector failure causes. This paper ad-dresses that gap. It proposes a seven-domain typology identifying ten specific AI-driven cyber governance failure causes grounded in public sector institutional analysis. It presents a three-pathway failure model showing how accountability failure, opera-tional resilience failure, and compliance failure interact and reinforce each other. It de-livers a structured coverage matrix testing five major governance frameworks (NIST CSF 2.0, ISO/IEC 27001, COBIT, NIST AI RMF, and ISO/IEC 42001) against the typology, finding that no instrument addresses Shadow AI, speed asymmetry, or gov-ernance vacuum at the operational specificity required for public sector application. The paper introduces speed asymmetry as a named structural construct with a specified mechanism. The framework provides the design specification for an AI-enabled cyber-security maturity model for government organizations.

LLMs are increasingly used for code generation in critical infrastructure, yet the security effect of domain-specific prompting is understudied. We present SecDrift, a benchmark measuring sector-conditioned security drift: the change in static-analysis vulnerability rates when prompts are conditioned on industry contexts versus neutral baselines. We evaluate 7 LLMs (6 producing analyzable code) across 8 CISA critical infrastructure sectors and 9 CWE categories with 5 replicates (5,355 evaluations), using a 5-dimension transformation with a matched-baseline condition that holds the task fixed while substituting only domain terminology. Industry prompts naively appear more secure (14.0% vs. 11.4%, -2.7pp), but the gap is not statistically significant (Fisher's exact p = 0.24, Cohen's h = -0.08) and is a composition artifact of two CWE categories: excluding CWE-502 and CWE-22 eliminates and slightly reverses it (+0.4pp, p = 1.00). A mixed-effects logistic regression confirms sector identity is not a moderator and localizes the only detectable condition effect to those two vulnerability types. 0 of 8 sectors show drift distinguishable from baseline, corrected or uncorrected (|h| < 0.15). A placebo on two non-CISA sectors (e-commerce, online education) reproduces the CISA industry rate almost exactly (10.5% vs. 11.4%, p = 0.63): the small pooled pattern reflects generic industry-framing specificity, not critical-infrastructure identity. In contrast, model selection has a large and consistent effect: among full-output models vulnerability rates range from 11.6% to 16.1%, and these differences persist across conditions. Model choice, not prompt framing, is the more reliable security lever. We release the framework, prompts, generated code, findings, human-validation verdicts, and analysis scripts.

The recently deployed Entry/Exit System (EES) introduces large-scale biometric verification into European border control, requiring face recognition systems to operate at extremely low false match rates (FMR). While regulatory frameworks define performance targets at the EES Central System level, they do not specify how verification thresholds should be calibrated in practice at the Member State level. In operational settings, obtaining representative real-world data for calibration is often constrained by legal, logistical, and privacy limitations. In this work, we investigate the use of synthetic face data for threshold calibration in document-to-live verification scenarios relevant to border control systems. We analyze the alignment of genuine and impostor score distributions between synthetic and real datasets and evaluate the transferability of calibrated thresholds across domains, with a focus on low-FMR operating points. Our results show that synthetic data can approximate calibration behavior in controlled settings, but fails to reliably generalize to unconstrained conditions due to mismatches in score distribution tails. These discrepancies lead to significant degradation in recognition performance and increased vulnerability to morph-based attacks. We further demonstrate that calibration outcomes are highly dataset-dependent, even across synthetic datasets. Overall, our findings highlight that while synthetic data is useful for system development and preliminary calibration, our results indicate that reliable threshold selection in high-security deployments typically requires validation and adjustment using representative real-world data.

Due to the lack of systematic evaluations, we are not yet able to determine which AI-based Windows malware detector to deploy in production, since existing evaluations (i) differ in terms of data used for both training and testing; (ii) do not consider temporal analysis to showcase whether models withstand the passage of time; (iii) avoid security evaluations with adversarial attacks that could highlight their brittleness against content-injection attacks; and (iv) neglect the computational requirements for deployment, risking slow inference on endpoints. For these reasons, we develop EXE-Bench, a comprehensive benchmark of AI-based Windows malware detectors. EXE-Bench assesses performance, temporal and adversarial robustness, and computational overhead, aggregating them into a single score for direct and fair model comparison. Through EXE-Bench, we highlight how evaluations conducted only after deployment are suboptimal and unable to provide a complete picture of their performance. In particular, through our analysis, we remark how much domain knowledge instilled through feature engineering is still extremely useful in this domain, resisting both time and adversarial attacks, in stark contrast with most of the deep networks that only excel right after deployment.