Security

Agentic AI governance is a critical component of agentic AI infrastructure ensuring that agents follow their owner's communication and interaction policies, and providing protection against attacks from malicious agents. The state-of-the-art solution, SAGA, assumes a logically centralized point of trust, the Provider, which serves as a repository for user and agent information and actively enforces policies. While SAGA provides protection against malicious agents, it remains vulnerable to a malicious Provider that deviates from the protocol, undermining the security of the identity and access control infrastructure. Deployment on both private and public clouds, each susceptible to insider threats, further increases the risk of Provider compromise. In this work, we analyze the attacks that can be mounted from a compromised Provider, taking into account the different system components and realistic deployments. We identify and execute several concrete attacks with devastating effects: undermining agent attributability, extracting private data, or bypassing access control. We then present three types of solutions for securing the Provider that offer different trade-offs between security and performance. We first present SAGA-BFT, a fully byzantine-resilient architecture that provides the strongest protection, but incurs significant performance degradation, due to the high-cost of byzantine resilient protocols. We then propose SAGA-MON and SAGA-AUD, two novel solutions that leverage lightweight server-side monitoring or client-side auditing to provide protection against most classes of attacks with minimal overhead. Finally, we propose SAGA-HYB, a hybrid architecture that combines byzantine-resilience with monitoring and auditing to trade-off security for performance. We evaluate all the architectures and compare them with SAGA. We discuss which solution is best and under what conditions.

Recent advances in Large Language Models (LLMs) have enabled agentic systems for complex, multi-step tasks; cybersecurity is emerging as a prominent application. To evaluate such agents, researchers widely adopt Capture The Flag (CTF) benchmarks. However, current CTF benchmarks reuse existing challenges, which exposes them to data contamination and potential cheating. Notably, we confirmed these issues in practice by integrating web search tools into an existing agent. To address these limitations, we present CTFusion, a streaming evaluation framework built on Live CTFs. To achieve this, CTFusion preserves per-agent independence under a single team account and reduces competition impact by forwarding only the first correct flag per challenge. Moreover, we implement CTFusion as a Model Context Protocol (MCP) server on the widely used CTFd platform, which offers broad applicability to diverse CTF events and agent types. Through experiments with three LLMs, two agents, and five Live CTFs, we demonstrate that existing CTF benchmarks can be unreliable in assessing LLM-based agents, while CTFusion can serve as a robust solution for evaluating cybersecurity agents. We release CTFusion as open source to foster future research in this area.

Large Language Models(LLMs) are increasingly explored for cybersecurity applications such as vulnerability detection. In the domain of threat modelling, prior work has primarily evaluated a number of general-purpose Large Language Models under limited prompting settings. In this study, we extend the research area of structured threat modelling by systematically evaluating domain-adapted language models of different sizes to their general counterparts. We use both LLMs and Small Language Models(SLMs) that were domain adapted to telecommunications and cybersecuirty. For the structured threat modelling, we selected the widely used STRIDE approach and the application area is 5G security. We present a comprehensive empirical evaluation using 52 different configurations (on 8 different language models) to analyze the impact of 1) domain adaptation, 2) model scale, 3) decoding strategies (greedy vs. stochastic sampling), and 4) prompting technique on STRIDE threat classification. Our results show that domain-adapted models do not consistently outperform their general-purpose counterparts, and decoding strategies significantly affect model behavior and output validity. They also show that while larger models generally achieve higher performance, these gains are neither consistent nor sufficient for reliable threat modelling. These findings highlight fundamental limitations of current LLMs for structured threat modelling tasks and suggest that improvements require more than additional training data or model scaling, motivating the need for incorporating more task-specific reasoning and stronger grounding in security concepts. We present insights on invalid outputs encountered and present suggestions for prompting tailored specifically for STRIDE threat modelling.

The rapid proliferation of LLM-based autonomous agents in real operating system environments introduces a new category of safety risk beyond content safety: behavior jailbreak, where an adversary induces an agent to execute dangerous OS-level operations with irreversible consequences. Existing benchmarks either evaluate safety at the semantic layer alone, missing physical-layer harms, or fail to isolate test cases, letting earlier runs contaminate later ones. We present LITMUS (LLM-agents In-OS Testing for Measuring Unsafe Subversion), a benchmark addressing both gaps via a semantic-physical dual verification mechanism and OS-level state rollback. LITMUS comprises 819 high-risk test cases organized into one harmful seed subset and six attack-extended subsets covering three adversarial paradigms (jailbreak speaking, skill injection, and entity wrapping), plus a fully automated multi-agent evaluation framework judging behavior at both conversational and OS-level physical layers. Evaluation across frontier agents reveals three findings: (1) current agents lack effective safety awareness, with strong models (e.g., Claude Sonnet 4.6) still executing 40.64% of high-risk operations; (2) agents exhibit pervasive Execution Hallucination (EH), verbally refusing a request while the dangerous operation has already completed at the system level, invisible to every prior semantic-only framework; and (3) skill injection and entity wrapping attacks achieve high success rates, exposing pronounced agent vulnerabilities. LITMUS provides the first standardized platform for reproducible, physically grounded behavioral safety evaluation of LLM agents in real OS environments.

Benchmarks for coding agents increasingly measure source-level software repair, and cybersecurity benchmarks increasingly measure broad capture-the-flag performance. Classical binary reverse engineering remains less precisely specified: given only an executable, can an agent recover validation logic and produce an input, serial, artifact, or key generator accepted by the program? We introduce CrackMeBench, a benchmark for evaluating language-model agents on educational CrackMe-style reverse-engineering tasks. CrackMeBench focuses on deterministic binary validation problems with executable oracles, symbol-poor binaries, explicit local tool access, and externally scored submissions rather than free-form explanations. The v0 benchmark combines eight public calibration CrackMes with twelve generated main-score tasks built from seeded C, Rust, and Go templates, and agents run through an equal shell interface in a no-network Linux Docker sandbox with standard reverse-engineering tools. In a three-model evaluation with a five-minute budget and three scored submissions per task, pass@3 on the generated split is 11/12 tasks (92%) for GPT-5.5, 7/12 (58%) for Claude Opus 4.7, and 5/12 (42%) for Kimi K2. The harder generated half separates the models more sharply, with pass@3 of 5/6, 2/6, and 1/6, respectively; on the eight-task public calibration split, pass@3 is 3/8, 2/8, and 1/8. CrackMeBench records pass@1 and pass@3, scored submissions, wall-clock time, command traces, tool categories, provider-reported token usage, estimated cost, and qualitative failure labels, providing a reproducible testbed for measuring progress from source-code reasoning toward autonomous binary analysis while restricting scope to educational, purpose-built programs.

Agentic language-model systems increasingly rely on mutable execution contexts, including files, memory, tools, skills, and auxiliary artifacts, creating security risks beyond explicit user prompts. This paper presents DeepTrap, an automated framework for discovering contextual vulnerabilities in OpenClaw. DeepTrap formulates adversarial context manipulation as a black-box trajectory-level optimization problem that balances risk realization, benign-task preservation, and stealth. It combines risk-conditioned evaluation, multi-objective trajectory scoring, reward-guided beam search, and reflection-based deep probing to identify high-value compromised contexts. We construct a 42-case benchmark spanning six vulnerability classes and seven operational scenarios, and evaluate nine target models using attack and utility grading scores. Results show that contextual compromise can induce substantial unsafe behavior while preserving user-facing task completion, demonstrating that final-response evaluation is insufficient. The findings highlight the need for execution-centric security evaluation of agentic AI systems. Our code is released at: https://github.com/ZJUICSR/DeepTrap

Tool-using LLM agents must act on untrusted webpages, emails, files, and API outputs while issuing privileged tool calls. Existing defenses often mediate trust at the granularity of an entire tool invocation, forcing a brittle choice in mixed-trust workflows: allow external content to influence a call and risk hijacked destinations or commands, or quarantine the call and block benign retrieval-then-act behavior. The key observation behind this paper is that indirect prompt injection becomes dangerous not when untrusted content appears in context, but when it determines an authority-bearing argument. We present \textsc{PACT} (\emph{Provenance-Aware Capability Contracts}), a runtime monitor that assigns semantic roles to tool arguments, tracks value provenance across replanning steps, and checks whether each argument's origin satisfies its role-specific trust contract. Under oracle provenance, \textsc{PACT} achieves 100% utility and 100% security on mixed-trust diagnostic suites, while flat invocation-level monitors incur false positives or false negatives. In full AgentDojo deployments across five models, \textsc{PACT} reaches 100% security on the three strongest models while recovering 38.1--46.4% utility, 8--16 percentage points above CaMeL at the same security level. Ablations show that both semantic roles and cross-step provenance are necessary. \textsc{PACT} reframes agent security as authority binding, and isolates the remaining deployment bottleneck to provenance inference and contract synthesis.

The growing integration of AI into cybersecurity is reshaping the balance between attackers and defenders. When access to advanced AI-enabled defence tools is uneven, resource-limited defenders may be unable to adopt effective protection, creating persistent system vulnerabilities. We study the impact of differential AI access using an evolutionary game-theoretic model in a finite population. We first show that when high-capability defence is costly, the population is driven toward low-cost, weak-defence behaviour, sustaining attacks and weakening long-run security. To address this problem, we introduce differential access to AI defence tools by allowing defenders to choose between low- and high-capability protection based on their resources. We then examine the role of a small group of committed defenders who always adopt strong defence and influence others through social learning. Although commitment increases the prevalence of strong defence, it alone cannot stabilise secure outcomes due to high defence costs. We therefore incorporate a targeted subsidy to remove the cost disadvantage from committed defenders. Our analysis shows that subsidised commitment significantly increases strong defence adoption, suppresses successful attacks, and improves overall system resilience. Simulations across a broad parameter space confirm that subsidies consistently outperform commitment alone. In addition, social-welfare analysis shows improved defender outcomes while keeping attacker gains low. These findings suggest that targeted support for key defenders can be an effective mechanism for stabilising cybersecurity in AI-driven environments and provide a theoretical bridge between cybersecurity policy, AI governance, and strategic allocation of defensive AI capabilities.

This position paper argues that the Authorization-Execution Gap (AEG) is a major safety and security problem in open-world agents. The AEG is the divergence between what a principal intends to authorize and what an open-world agent ultimately executes. Because such agents act autonomously across tools, persistent state, and multi-agent handoffs, even small instances of authorization divergence can cause harm that is difficult or impossible to undo. We argue that many observed agent failures can be traced to three structural sources of AEG: delegation-level incompleteness, channel-level corruption, and composition-level fragmentation. The same observed failure may arise from any of these sources. Without identifying the source, a defense targeting the symptom alone cannot address the underlying cause. Agent safety and security should therefore emphasize source-oriented diagnosis and defense. Because the structural sources of AEG arise dynamically during execution, this approach necessarily requires authorization integrity checks applied during execution, rather than relying solely on one-shot upfront filtering or post-hoc audit. For NeurIPS, the implication is that papers on open-world agents should report not only outcome-level metrics such as task success or attack resistance, but also process-level evidence showing where AEG was detected, constrained, and attributed to a structural source during execution.

Agent benchmarks typically report only final outcomes: pass or fail. This threatens evaluation credibility in three ways. First, scores may be inflated or deflated by shortcuts and benchmark artifacts, misrepresenting capability. Second, benchmark performance may fail to predict real-world utility due to scaffold limitations and recurring failure modes. Finally, capability scores may conceal dangerous or catastrophic actions taken by the agent. We argue that log analysis -- the systematic tracking and analysis of the inputs, execution, and outputs of an AI agent -- is necessary to overcome these validity threats and promote credible agent evaluation. In this paper, we (1) present a taxonomy of threats to credible evaluation documented through log analysis, and (2) develop a set of guiding principles for log analysis. We illustrate these principles on tau-Bench Airline, revealing that pass^5 performance was under-elicited by nearly 50% and surfacing deployment failure modes invisible to outcome metrics. We conclude with pragmatic recommendations to increase uptake of log analysis, directed at diverse stakeholders including benchmark creators, model developers, independent evaluators, and deployers.

AI measurement science has a wide variety of methodologies and measurements for comparing AI systems, resulting in what often appear to be "apples-to-oranges" comparisons across AI evaluations. To move toward "apples-to-apples" comparisons in real-world AI evaluations, this work advocates for methodological transparency in evaluation scenarios, operational grounding, and human-centered design (HCD) principles. We propose a repeatable process for transforming high-level use cases to detailed scenarios by eliciting use cases from subject matter experts (SMEs) via a structured AI Use Case Worksheet with six key elements: use case, sector, user (direct and indirect), intended outcomes, expected impacts (positive and negative), and KPIs and metrics. We demonstrate utility of the worksheet and process in the U.S. financial services sector. This paper reports on example high-level AI use cases identified by financial services sector SMEs: cyber defense enablement, developer productivity, financial crime aggregation, suspicious activity report (SAR) filing, credit memo generation, and internal call center support. These AI use cases provided are illustrative of the process and not exhaustive. Central to our work is a three-stage expansion pipeline combining LLM prompting with human reviews to generate 107 scenarios from those use cases elicited from SMEs. This process integrates iterative human reviews at every juncture to ensure operational grounding: for scenario titles and descriptions; for core scenario elements like users, benefits and risks, and metrics; and for scenario narratives and evaluation objectives. Human checkpoints ensure scenarios remain reflective of real-world usage and human needs. We describe a validation rubric to assess scenario quality. By defining key scenario components, this work supports a more consistent and meaningful paradigm for human-centered AI evaluations.

Modern cybersecurity relies heavily on static machine-learning-based malware classifiers. However, transformations such as packing and other non-semantic modifications applied to executable files limit their reliability. Malware classifiers often learn these unnecessary artifacts rather than the true binary behavior because of the high association between maliciousness and packing. Moreover, these malware classifiers are black boxes, making it difficult to understand what they learn. To address this issue, we proposed a two-part framework using the post-hoc interpretability XAI tool TRUSTEE, followed by a manual analysis of the top features. We conducted several controlled experiments by varying the dataset composition ratios to understand their impact on the results. The top-ranked features across all experiments, identified by TRUSTEE, were predominantly packing artifacts, portable executable(PE) metadata, and n-grams at the string level, rather than malicious semantics. These results suggest that these malware classifiers are highly sensitive to dataset composition and can misinterpret packing as malicious behavior. Our proposed framework allows for the reproducible diagnosis of such biases and forms a guideline for building more robust and semantically meaningful malware detection models

Motivated by the challenge to improve the adversarial robustness, security, and trust of medical decision making intelligent agents, this study develops a full-link security enhancement framework, which describes "input risk perception - medical evidence constraint - knowledge consistency verification - decision confidence reweighting - security output control - adversarial feedback update." We propose ARSM-Agent and define a weighted joint objective consisting of decision accuracy loss, adversarial robustness loss, safety refusal loss, and knowledge consistency loss, with weights of 0.3, 0.3, 0.2, and 0.2, respectively. The whole medical decision formulation is implemented by multi-module collaborative linkage. We verify that the algorithm is more efficient than four baselines, including LLM-Agent, Retrieval-Agent, Filter-Agent, and Adv-Train-Agent. Under semantic perturbation, prompt injection, drug-name confusion, and false-evidence attacks, ARSM-Agent reduces the overall attack success rate to 8.7% and achieves a knowledge consistency score of 0.91. Ablation experiments quantify each module's contribution: removing risk perception, evidence retrieval, consistency verification, and confidence reweighting reduces accuracy by 6.7%, 9.1%, 7.6%, and 4.4%, respectively, and increases attack success rate by 13.8%, 11.1%, 8.6%, and 6.9%. The proposed approach addresses key security issues of medical decision making intelligent agents, obtains secure decision making in challenging scenarios, and provides reliable intelligent support for medical decision-making intelligent agents.

Research artifacts are widely shared to support reproducibility, and artifact evaluation (AE) has become common at many leading conferences. However, AE mainly checks whether artifacts work as claimed and can be reproduced. It does not aim at spotting or mitigitating potential security risks. Since these artifacts are publicly released and reused, they may unintentionally create opportunities for misuse and raise concerns about safe and responsible sharing. We study 1,388 research artifacts published between 2023 and 2025 at the top-4 security conferences, perform static analysis, and obtain 132,431 candidate security findings. We propose a taxonomy for context-aware security assessment and examine the findings to filter false positives and identify findings that represent plausible context-dependent security risks. We find that 44.80% of the reviewed findings are security-relevant. To support scalable analysis, we present SAFE (Security-Aware Framework for Artifact Evaluation), an autonomous framework that assesses tool-reported findings based on code semantics, execution context, and practical exploitability. SAFE achieves 94.40% accuracy and a 93.60% F1-score in distinguishing security-relevant from non-security findings, and 92.40% accuracy and an 81.10% F1-score in classifying security-risk types. Overall, our results show that context-aware security assessment is a practical complement to existing AE processes and can support safer and more responsible research artifact sharing. The source code for SAFE is available at: https://github.com/nanda-rani/SAFE

Agentic AI systems can plan, call tools, inspect code, interact with web applications, and coordinate multi-step workflows. These same capabilities change the economics of cyber offense. The central near-term risk is not that every low-skill criminal immediately becomes a frontier exploit researcher; it is that agentic AI compresses the attack lifecycle by lowering the cost of reconnaissance, phishing, credential abuse, vulnerability triage, exploit adaptation, and post-compromise decision support. This paper synthesizes current public evidence from national cybersecurity agencies, industry threat reports, agent security guidance, and research on LLM agents cyber capabilities. It introduces a Three Channel Agentic Cyber Risk Model and an Agentic Attack Compression Model, uses the 2026 Linux kernel Copy Fail incident as a case study for foothold-to-root acceleration, and develops a 2026 to 2028 forecast for large enterprises and the German and European Mittelstand. The paper concludes with a prioritized defense roadmap. Organizations should treat agentic AI security as an immediate operational problem: identity, phishing resistant authentication, patch velocity, CI/CD and Linux/container hardening, agent governance, telemetry, and recovery readiness must be strengthened now.

Enterprise agents increasingly operate inside scoped retrieval systems, delegated workflows, and policy-constrained evidence environments. In these settings, access control can be enforced correctly while the system still produces an answer that appears complete even though material evidence lies outside the caller's authorization boundary. This paper introduces Partial Evidence Bench, a deterministic benchmark for measuring that failure mode. The benchmark ships three scenario families -- due diligence, compliance audit, and security incident response -- with 72 tasks total, ACL-partitioned corpora, oracle complete answers, oracle authorized-view answers, oracle completeness judgments, and structured gap-report oracles. It evaluates systems along four surfaces: answer correctness, completeness awareness, gap-report quality, and unsafe completeness behavior. Checked-in baselines show that silent filtering is catastrophically unsafe across all shipped families, while explicit fail-and-report behavior eliminates unsafe completeness without collapsing the task into trivial abstention. Preliminary real-model runs show model-dependent and scenario-sensitive differences in whether systems overclaim completeness, conservatively underclaim, or report incompleteness in an enterprise-usable form. The benchmark's broader contribution is to make a governance-critical agent failure measurable without human judges or contamination-prone static corpora.

For Transformer models, cryptographically secure inference ensures that the client learns only the final output, while the server learns nothing about the client's input. However, securely computing nonlinear layers remains a major efficiency bottleneck due to the substantial communication rounds and data transmission required. To address this issue, prior works reveal intermediate activations to the client, allowing nonlinear operations to be computed in plaintext. Although this approach significantly improves efficiency, exposing activations enables adversaries to extract model weights. To mitigate this risk, existing works employ a shuffling defense that reveals only randomly permuted activations to the client. In this work, we show that the shuffling defense is not as robust as previously claimed. We propose an attack that aligns differently shuffled activations to a common permutation and subsequently exploits them to extract model weights. Experiments on Pythia-70m and GPT-2 demonstrate that the proposed attack can align shuffled activations with mean squared errors ranging from $10^{-9}$ to $10^{-6}$. With a query cost of approximately $1, the adversary can recover model weights with L1-norm differences ranging from $10^{-4}$ to $10^{-2}$ compared to the oracle weights.

AI agents are increasingly deployed across diverse domains to automate complex workflows through long-horizon and high-stakes action executions. Due to their high capability and flexibility, such agents raise significant security and safety concerns. A growing number of real-world incidents have shown that adversaries can easily manipulate agents into performing harmful actions, such as leaking API keys, deleting user data, or initiating unauthorized transactions. Evaluating agent security is inherently challenging, as agents operate in dynamic, untrusted environments involving external tools, heterogeneous data sources, and frequent user interactions. However, realistic, controllable, and reproducible environments for large-scale risk assessment remain largely underexplored. To address this gap, we introduce the DecodingTrust-Agent Platform (DTap), the first controllable and interactive red-teaming platform for AI agents, spanning 14 real-world domains and over 50 simulation environments that replicate widely used systems such as Google Workspace, Paypal, and Slack. To scale the risk assessment of agents in DTap, we further propose DTap-Red, the first autonomous red-teaming agent that systematically explores diverse injection vectors (e.g., prompt, tool, skill, environment, combinations) and autonomously discovers effective attack strategies tailored to varying malicious goals. Using DTap-Red, we curate DTap-Bench, a large-scale red-teaming dataset comprising high-quality instances across domains, each paired with a verifiable judge to automatically validate attack outcomes. Through DTap, we conduct large-scale evaluations of popular AI agents built on various backbone models, spanning security policies, risk categories, and attack strategies, revealing systematic vulnerability patterns and providing valuable insights for developing secure next-generation agents.

Modern AI agents execute real-world side effects through tool calls such as file operations, shell commands, HTTP requests, and database queries. A single unsafe action, including accidental deletion, credential exposure, or data exfiltration, can cause irreversible harm. Existing defenses are incomplete: post-hoc benchmarks measure behavior after execution, static guardrails miss obfuscation and multi-step context, and infrastructure sandboxes constrain where code runs without understanding what an action means. We present AgentTrust, a runtime safety layer that intercepts agent tool calls before execution and returns a structured verdict: allow, warn, block, or review. AgentTrust combines a shell deobfuscation normalizer, SafeFix suggestions for safer alternatives, RiskChain detection for multi-step attack chains, and a cache-aware LLM-as-Judge for ambiguous inputs. We release a 300-scenario benchmark across six risk categories and an additional 630 independently constructed real-world adversarial scenarios. On the internal benchmark, the production-only ruleset achieves 95.0% verdict accuracy and 73.7% risk-level accuracy at low-millisecond end-to-end latency. On the 630-scenario benchmark, evaluated under a patched ruleset and not claimed as zero-shot, AgentTrust achieves 96.7% verdict accuracy, including about 93% on shell-obfuscated payloads. AgentTrust is released under the AGPL-3.0 license and provides a Model Context Protocol server for MCP-compatible agents.

Cyber threats are rapidly increasing, expanding their impact from large-scale enterprises to government services and individual users, making robust security systems increasingly essential. However, a significant shortage of skilled cybersecurity professionals exacerbates this challenge. While recent research has explored automating tasks such as penetration testing using LLM-based agents, existing frameworks often perform poorly due to limited capability in strategy formulation, domain-specific reasoning, and accurate action and tool selection. To overcome these limitations, we propose Pen-Strategist framework, consisting of a novel domain-specific reasoning model that derives pentesting strategies via logical reasoning and a classifier that converts the strategies into actionable steps. First, we construct a reasoning dataset containing logical explanations for both strategy derivation and step selection in pentesting scenarios. We then fine-tune a Qwen-3-14B model for strategy generation using reinforcement learning. Evaluation on the test split of the dataset demonstrates a 87% improvement in strategy derivation performance compared to the baseline. Furthermore, we integrate the fine-tuned Pen-Strategist model into existing automated pentesting frameworks, such as PentestGPT, and evaluate its performance on vulnerable machines, achieving a 47.5% improvement in subtask completion while surpassing the baseline GPT-5. Further experiments on the CTFKnow benchmark show an 18% performance gain over the base model. For step prediction, we train a semantic-based CNN classifier, which outperforms commercial LLMs by 28% and enhances execution stability. Finally, we conduct a user study to qualitatively assess the generated strategies, and Pen-Strategist demonstrates superior performance compared to the Claude-4.6-Sonnet.

European financial institutions face mounting regulatory pressure while their security operations centres remain constrained not by data or staffing but by reasoning capacity: enterprise SIEMs cover only a fraction of MITRE ATT&CK techniques, two thirds of SOC teams cannot keep pace with alert volumes, and the majority of breaches are preceded by alerts that are generated but never investigated. Frontier large language models now achieve state-of-the-art results on isolated cybersecurity tasks (one-day vulnerability exploitation, code-level patching, intrusion detection) yet no narrow win constitutes a platform that can compose across functions, persist multi-tenant state, map findings to regulatory regimes and survive an audit. This position paper argues that the right unit of construction is a hybrid multi-agent system in which specialised LLM subagents reason over classical SIEM/XDR telemetry rather than replacing it, share accumulated agent state across institutions through privacy-preserving federation, and can connect to complementary capability packs such as quantum-based authentication, digital twins for adversarial validation, and eBPF-based kernel telemetry. We present CyberAId, a model-agnostic, on-premise-deployable platform in which a Main Agent coordination layer, a Reporting capability, and specialist subagents operate within a shared runtime under bounded human-in-the-loop autonomy, organised around four falsifiable design principles, and aligned with relevant regulations. CyberAId will be validated at four representative financial use cases (client impersonation, anti-money-laundering for payment service providers, retail-banking incident response, and high-frequency-trading resilience) and propose skill-based agent adaptation as the most promising research direction for turning each deployment into a contribution to a continuously refined collective defence.

We present XekRung, a frontier large language model for cybersecurity, designed to provide comprehensive security capabilities. To achieve this, we develop diverse data synthesis pipelines tailored to the cybersecurity domain, enabling the scalable construction of high-quality training data and providing a strong foundation for cybersecurity knowledge and understanding. Building on this foundation, we establish a complete training pipeline spanning continued pre-training (CPT), supervised fine-tuning (SFT), and reinforcement learning (RL) to further extend the model's capabilities. We further introduce a multi-dimensional evaluation system to guide the iterative improvement of both domain-specific and general-purpose abilities. Extensive experiments demonstrate that XekRung achieves state-of-the-art performance on cybersecurity-specific benchmarks among models of the same scale, while maintaining strong performance on general benchmarks.

Autonomous agent frameworks built upon large language models (LLMs) are evolving into complex, tool-integrated, and continuously operating systems, introducing security risks beyond traditional prompt-level vulnerabilities. As this paradigm is still at an early stage of development, a timely and systematic understanding of its security implications is increasingly important. Although a growing body of work has examined different attack surfaces and defense problems in agent systems, existing studies remain scattered across individual aspects of agent security, and there is still a lack of a layered review on this topic. To address this gap, this survey presents a layered review of security risks and defense strategies in autonomous agent frameworks, with OpenClaw as a case study. We organize the analysis into four security-relevant layers: the context and instruction layer, the tool and action layer, the state and persistence layer, and the ecosystem and automation layer. For each layer, we summarize its functional role, representative security risks, and corresponding defense strategies. Based on this layered analysis, we further identify that threats in autonomous agent frameworks may propagate across layers, from manipulated inputs to unsafe actions, persistent state contamination, and broader ecosystem-level impact. Finally, we highlight potential key challenges, including research imbalance across layers, the lack of long-horizon evaluation, and weak ecosystem trust models, and outline future directions toward more systematic and integrated defenses.

Security Operations Centers (SOCs) face mounting operational challenges. These challenges come from increasing threat volumes, heterogeneous SIEM platforms, and time-consuming manual triage workflows. We present an end-to-end threat management framework that integrates ensemble-based detection, syntax-constrained query generation, and retrieval-augmented resolution support to automate critical security workflows. Our detection module evaluates both traditional machine learning classifiers and large language models (LLMs), then combines the three best-performing LLMs to create an ensemble model, achieving 82.8% accuracy while maintaining 0.120 false positive rate on SIEM logs. We introduce the SQM (Syntax Query Metadata) architecture for automated evidence collection. It uses platform-specific syntax constraints, metadata-based retrieval, and documentation-grounded prompting to generate executable queries for IBM QRadar and Google SecOps. SQM achieves a BLEU score of 0.384 and a ROUGE-L score of 0.731. These results are more than twice as good as the baseline LLM performance. For incident resolution and recommendation generation, we demonstrate that integrating SQM-derived evidence improves resolution code prediction accuracy from 78.3% to 90.0%, with an overall recommendation quality score of 8.70. In production SOC environments, our framework reduces average incident triage time from hours to under 10 minutes. This work demonstrates that domain-constrained LLM architectures with retrieval augmentation can meet the strict reliability and efficiency requirements of operational security environments at scale.

Recent advances in large language models and agentic frameworks have enabled virtual customer assistants (VCAs) for complex support. We present SecMate, a multi-agent VCA for cybersecurity troubleshooting that integrates device, user, and service specificity from conversational and device-level signals. Device specificity is provided by a lightweight local diagnostic utility, while user specificity relies on implicit proficiency inference and profile-aware troubleshooting. Service specificity is achieved through a proactive, context-aware recommender. We evaluate SecMate in a controlled study with 144 participants and 711 conversations. Device-level evidence increased correct resolutions from about 50% to over 90% relative to an LLM-only baseline, while step-by-step guidance improved pleasantness and reduced user burden. The recommender achieved high relevance (MRR@1=0.75), and participants showed strong willingness to substitute human IT support at costs well below human benchmarks. We release the full code base and a richly annotated dataset to support reproducible research on adaptive VCAs.

Structured-workflow agents driven by large language models execute tool calls against sensitive external environments. We propose \codename, a telemetry-driven behavioral anomaly detection firewall. Drawing on sequence-based intrusion detection, \codename\ compiles verified benign tool-call telemetry into a parameterized deterministic finite automaton (pDFA). The model defines permitted tool sequences, sequential contexts, and parameter bounds. At runtime, a lightweight gateway enforces these boundaries via an $O(1)$ state-transition structural lookup, shifting computationally expensive analysis entirely offline. Evaluated on the Agent Security Bench (ASB), \codename\ achieves a 5.6% macro-averaged attack success rate (ASR) across five scenarios. Within three structured workflows, ASR drops to 2.2%, outperforming Aegis, a state-of-the-art stateless scanner, at 12.8%. \codename\ achieves 0% ASR on multi-step and context-sequential attacks in structured settings. Furthermore, against 1,000 algorithmically spliced exfiltration payloads, only 1.4% matched valid structural paths, all of which failed end-to-end string parameter guards (0 successes out of 14 surviving paths, 95% CI [0%, 23.2%]). \codename\ introduces just 2.2~ms of per-call latency (a 3.7$\times$ speedup over \textsc{Aegis}) while maintaining a 2.0% benign task failure rate (BTFR) on benign workloads. Modeling the behavioral trajectory effectively collapses the available attack surface, but unmaintained continuous parameter bounds remain vulnerable to synonym-substitution attacks (18% evasion rate). Thus, exact-match whitelisting of sensitive parameters ultimately bears the final defensive load against execution.

The security of open-source software repositories is increasingly threatened by next-gen software supply chain attacks. These attacks include multiphase malware execution, remote access activation, and dynamic payload generation. Traditional Machine Learning (ML) detectors struggle to detect these attacks due to the high-dimensional and sparse nature of dynamic behavioral data, including system calls, network traffic, directory access patterns, and dependency logs. As a result, these data characteristics degrade the performance, stability, and explainability of ML models. These challenges have made Deep Learning (DL) a promising alternative, given its success across various domains and its potential for modeling complex patterns. This paper presents eDySec, a DL-based efficient, stable, and explainable framework for dynamic behavioral analysis to detect malicious packages. Using the QUT-DV25 dataset, which captures both install-time and post-installation behaviors of packages, we evaluate DL models and investigate feature sets to identify the most discriminative attributes for enabling efficient malicious package detection. Additionally, model stability analysis and explainable AI techniques are incorporated into the detection pipeline to enable stable, and transparent interpretations of model decisions. Experimental results demonstrate that eDySec significantly outperforms the state-of-the-art frameworks. Specifically, it halves feature dimensionality while lowering false positives by 82% and false negatives by 79%. It also improves accuracy by 3%, achieves near-perfect stability, and maintains an inference latency of 170ms per package. Further analysis reveals that feature and model selection play a critical role, as certain combinations degrade performance. Ultimately, this study advances the understanding of the strengths and limitations of dynamic analysis against next-gen attacks.

This report presents a comparative evaluation of DKnownAI Guard in AI agent security scenarios, benchmarked against three competing products: AWS Bedrock Guardrails, Azure Content Safety, and Lakera Guard. Using human annotation as the ground truth, we assess each guardrail's ability to detect two categories of risks: threats to the agent itself (e.g., instruction override, indirect injection, tool abuse) and requests intended to elicit harmful content (e.g., hate speech, pornography, violence). Evaluation results demonstrate that DKnownAI Guard achieves the highest recall rate at 96.5% and ranks first in true negative rate (TNR) at 90.4%, delivering the best overall performance among all evaluated guardrails.

Auditing the semantic properties of proprietary data creates a fundamental tension: verification requires transparent access, while proprietary rights demand confidentiality. While Zero-Knowledge Proofs (ZKPs) ensure privacy, they are typically limited to precise algebraic constraints and are ill-suited for verifying qualitative, unstructured properties, such as the logic within a codebase. We propose {\em Agentic Witnessing}, a framework that moves verification from attested execution to {\em attested reasoning}. The system is composed of three agents: a Verifier (who wants to check properties of a dataset), a Prover (who owns the dataset) and an Auditor (that inspects the dataset). The Verifier is allowed to ask a limited number of simple binary true/false questions to the auditor. By isolating an LLM-based Auditor within a Trusted Execution Environment (TEE), the system enables the Verifier to query a Prover's private data via simple Boolean queries, without exposing the raw dataset. The Auditor uses the Model Context Protocol (MCP) to dynamically inspect the target dataset, producing a yes/no verdict accompanied by a cryptographic transcript: a signed hash chain binding the reasoning trace to both the original dataset and the TEE's hardware root of trust. We demonstrate this architecture by automating the artifact evaluation process for 21 peer-reviewed computer science papers with released codebases on GitHub (e.g. Does the codebase implement the system described in the paper?). We verified five high-level properties of these codebases described in the corresponding publications, treating the source code as private. Our results show that TEE-enabled agentic auditing provides a mechanism for privacy-preserving oversight, effectively decoupling qualitative verification from the need for data disclosure.

Multi-agent systems (MAS), composed of networks of two or more autonomous AI agents, have become increasingly popular in production deployments, yet introduce security risks that do not arise in single-agent settings. Even if individual agents exhibit robust security, architectural decisions governing their coordination can create attack surfaces that have not been systematically characterized. In this work, we present an empirical study of how MAS design decisions shape the tradeoff between task performance and attack resistance. Across three agentic environments (browser, desktop, and code) and 13 architectural configurations, we use stagewise evaluations that distinguish planning refusal, execution-stage interception, partial harmful execution, and successful attack completion to study three key design choices: (i) agent roles, which determine how authority and responsibility are allocated; (ii) communication topology, which shapes how and when agents interact; and (iii) memory, which determines the context and state visibility accessible to each agent. We find that multi-agent architectures are more vulnerable than standalone agents in the majority of configurations, with attack success rates varying by up to 3.8x at comparable or higher benign accuracy, and that no single design is universally safer. These results motivate the development of further evaluations that move beyond the security properties of a single agent.

Firms are deploying more capable AI systems, but organizational controls often have not kept pace. These systems can generate greater productivity gains, but high-value uses require broader authority exposure -- data access, workflow integration, and delegated authority -- when governance controls have not yet decoupled capability from authority exposure. We develop an analytical model in which a firm jointly chooses AI deployment and cybersecurity investment under this governance-capability gap. The central result shows a deployment paradox: in high-loss environments, better AI can lead a firm to deploy less when capability is deployed through broader authority exposure under weak governance. Optimal deployment also falls below the no-risk benchmark, and this shortfall widens with breach-loss magnitude and with the authority exposure attached to more capable systems. Governance investment that reduces breach-loss magnitude shrinks the paradox region itself, while breach externalities expand the range of environments in which deployment is socially constrained. Governance maturity is therefore not merely a constraint on AI adoption. It is a condition that shapes whether capability improvements translate into productive deployment.

Current text anonymization evaluation relies on span-based metrics that fail to capture what an adversary could actually infer, and assumes a single data subject, ignoring multi-subject scenarios. To address these limitations, we present SPIA (Subject-level PII Inference Assessment), the first benchmark that shifts the unit of evaluation from text spans to individuals, comprising 675 documents across legal and online domains with novel subject-level protection metrics. Extensive experiments show that even when over 90% of PII spans are masked, subject-level inference protection drops as low as 33%, leaving the majority of personal information recoverable through contextual inference. Furthermore, target-subject-focused anonymization leaves non-target subjects substantially more exposed than the target subject. We show that subject-level inference-based evaluation is essential for ensuring safe text anonymization in real-world settings.

As artificial intelligence (AI) systems are increasingly deployed across critical domains, their security vulnerabilities pose growing risks of high-profile exploits and consequential system failures. Yet systematic approaches to evaluating AI security remain underdeveloped. In this paper, we introduce AVISE (AI Vulnerability Identification and Security Evaluation), a modular open-source framework for identifying vulnerabilities in and evaluating the security of AI systems and models. As a demonstration of the framework, we extend the theory-of-mind-based multi-turn Red Queen attack into an Adversarial Language Model (ALM) augmented attack and develop an automated Security Evaluation Test (SET) for discovering jailbreak vulnerabilities in language models. The SET comprises 25 test cases and an Evaluation Language Model (ELM) that determines whether each test case was able to jailbreak the target model, achieving 92% accuracy, an F1-score of 0.91, and a Matthews correlation coefficient of 0.83. We evaluate nine recently released language models of diverse sizes with the SET and find that all are vulnerable to the augmented Red Queen attack to varying degrees. AVISE provides researchers and industry practitioners with an extensible foundation for developing and deploying automated SETs, offering a concrete step toward more rigorous and reproducible AI security evaluation.

Adversarial robustness evaluation underpins every claim of trustworthy ML deployment, yet the field suffers from fragmented protocols and undetected gradient masking. We make two contributions. (1) Structured synthesis. We analyze nine peer-reviewed corpus sources (2020--2026) through seven complementary protocols, producing the first end-to-end structured analysis of the field's consensus and unresolved challenges. (2) Auto-ART framework. We introduce Auto-ART, an open-source framework that operationalizes identified gaps: 50+ attacks, 28 defense modules, the Robustness Diagnostic Index (RDI), and gradient-masking detection. It supports multi-norm evaluation (l1/l2/linf/semantic/spatial) and compliance mapping to NIST AI RMF, OWASP LLM Top 10, and the EU AI Act. Empirical validation on RobustBench demonstrates that Auto-ART's pre-screening identifies gradient masking in 92% of flagged cases, and RDI rankings correlate highly with full AutoAttack. Multi-norm evaluation exposes a 23.5 pp gap between average and worst-case robustness on state-of-the-art models. No prior work combines such structured meta-scientific analysis with an executable evaluation framework bridging literature gaps into engineering.

The rapid evolution and use of Large Language Models (LLMs) in professional workflows require an evaluation of their domain-specific knowledge against industry standards. We introduceCyberCertBench, a new suite of Multiple Choice Question Answering (MCQA) benchmarks derived from industry recognized certifications. CyberCertBench evaluates LLM domain knowledgeagainst the professional standards of Information Technology cybersecurity and more specializedareas such as Operational Technology and related cybersecurity standards. Concurrently, we propose and validate a novel Proposer-Verifier framework, a methodology to generate interpretable,natural language explanations for model performance. Our evaluation shows that frontier modelsachieve human expert level in general networking and IT security knowledge. However, theiraccuracy declines in questions that require vendor-specific nuances or knowledge in formalstandards, like, e.g., IEC 62443. Analysis of model scaling trend and release date demonstratesremarkable gains in parameter efficiency, while recent larger models show diminishing returns.Code and evaluation scripts are available at: https://github.com/GKeppler/CyberCertBench.

For LLM agents, memory management critically impacts efficiency, quality, and security. While much research focuses on retention, selective forgetting--inspired by human cognitive processes (hippocampal indexing/consolidation theory and Ebbinghaus forgetting curve)--remains underexplored. We argue that in resource-constrained environments, a well-designed forgetting mechanism is as crucial as remembering, delivering benefits across three dimensions: (1) efficiency via intelligent memory pruning, (2) quality by dynamically updating outdated preferences and context, and (3) security through active forgetting of malicious inputs, sensitive data, and privacy-compromising content. Our framework establishes a taxonomy of forgetting mechanisms: passive decay-based, active deletion-based, safety-triggered, and adaptive reinforcement-based. Building on advances in LLM agent architectures and vector databases, we present detailed specifications, implementation strategies, and empirical validation from controlled experiments. Results show significant improvements: access efficiency (+8.49%), content quality (+29.2% signal-to-noise ratio), and security performance (100% elimination of security risks). Our work bridges cognitive neuroscience and AI systems, offering practical solutions for real-world deployment while addressing ethical and regulatory compliance. The paper concludes with challenges and future directions, establishing selective forgetting as a fundamental capability for next-generation LLM agents operating in real-world, resource-constrained scenarios. Our contributions align with AI-native memory systems and responsible AI development.

Logging code plays an important role in software systems by recording key events and behaviors, which are essential for debugging and monitoring. However, insecure logging practices can inadvertently expose sensitive information or enable attacks such as log injection, posing serious threats to system security and privacy. Prior research has examined general defects in logging code, but systematic analysis of logging code security issues remains limited, particularly in leveraging LLMs for detection and repair. In this paper, we derive a comprehensive taxonomy of logging code security issues, encompassing four common issue categories and 10 corresponding patterns. We further construct a benchmark dataset with 101 real-world logging security issue reports that have been manually reviewed and annotated. We then propose an automated framework that incorporates various contextual knowledge to evaluate LLMs' capabilities in detecting and repairing logging security issues. Our experimental results reveal a notable disparity in performance: while LLMs are moderately effective at detecting security issues (e.g., the accuracy ranges from 12.9% to 52.5% on average), they face noticeable challenges in reliably generating correct code repairs. We also find that the issue description alone improves the LLMs' detection accuracy more than the security pattern explanation or a combination of both. Overall, our findings provide actionable insights for practitioners and highlight the potential and limitations of current LLMs for secure logging.

Security Operations Centers (SOCs) increasingly encounter difficulties in correlating heterogeneous alerts, interpreting multi-stage attack progressions, and selecting safe and effective response actions. This study introduces AgentSOC, a multi-layered agentic AI framework that enhances SOC automation by integrating perception, anticipatory reasoning, and risk-based action planning. The proposed architecture consolidates several layers of abstraction to provide a single operational loop to support normalizing alerts, enriching context, generating hypotheses, validating structural feasibility, and executing policy-compliant responses. Conceptually evaluated within a large enterprise environment, AgentSOC improves triage consistency, anticipates attackers' intentions, and provides recommended containment options that are both operationally feasible and well-balanced between security efficacy and operational impact. The results suggest that hybrid agentic reasoning has the potential to serve as a foundation for developing adaptive, safer SOC automation in large enterprises. Additionally, a minimal Proof-Of-Concept (POC) demonstration using LANL authentication data demonstrated the feasibility of the proposed architecture.

We introduce the Cyber Defense Benchmark, a benchmark for measuring how well large language model (LLM) agents perform the core SOC analyst task of threat hunting: given a database of raw Windows event logs with no guided questions or hints, identify the exact timestamps of malicious events. The benchmark wraps 106 real attack procedures from the OTRF Security-Datasets corpus - spanning 86 MITRE ATT&CK sub-techniques across 12 tactics - into a Gymnasium reinforcement-learning environment. Each episode presents the agent with an in-memory SQLite database of 75,000-135,000 log records produced by a deterministic campaign simulator that time-shifts and entity-obfuscates the raw recordings. The agent must iteratively submit SQL queries to discover malicious event timestamps and explicitly flag them, scored CTF-style against Sigma-rule-derived ground truth. Evaluating five frontier models - Claude Opus 4.6, GPT-5, Gemini 3.1 Pro, Kimi K2.5, and Gemini 3 Flash - on 26 campaigns covering 105 of 106 procedures, we find that all models fail dramatically: the best model (Claude Opus 4.6) submits correct flags for only 3.8% of malicious events on average, and no run across any model ever finds all flags. We define a passing score as >= 50% recall on every ATT&CK tactic - the minimum bar for unsupervised SOC deployment. No model passes: the leader clears this bar on 5 of 13 tactics and the remaining four on zero. These results suggest that current LLMs are poorly suited for open-ended, evidence-driven threat hunting despite strong performance on curated Q&A security benchmarks.

We release Terminal Wrench, a subset of 331 terminal-agent benchmark environments, copied from the popular open benchmarks that are demonstrably reward-hackable. The data set includes 3,632 hack trajectories and 2,352 legitimate baseline trajectories across three frontier models (Claude Opus 4.6, Gemini 3.1 Pro, GPT-5.4). Each entry preserves the original task definition alongside full attack trajectories that show how the verifier was bypassed. It also includes cases where the task was not solved as intended. The tasks span system administration, machine learning, software engineering, and security challenges; the exploits range from simple output spoofing to stack-frame introspection, standard-library patching, and rootkit-style binary hijacking. Crucially, these exploits are specific to each task, rather than the evaluation harness, making them harder to patch. We also present a monitorability study in which hack trajectories are sanitized or stripped of reasoning traces and then scored by an LLM judge, showing that detection degrades meaningfully when chain-of-thought is removed (AUC drops from 0.97 to 0.92). The data set is publicly available at https://github.com/few-sh/terminal-wrench.

Users increasingly rely on consumer-facing generative AI (GenAI) for tasks ranging from everyday needs to sensitive use cases. Yet, it remains unclear whether and how existing security and privacy (S&P) communications in GenAI tools shape users' adoption decisions and experiences. Understanding how users seek, interpret, and evaluate S&P information is critical for designing usable transparency that users can trust and act on. We conducted semi-structured interviews and design sessions with 21 U.S. GenAI users. Our findings suggest that available S&P information rarely drove initial adoption in practice, as participants often perceived it as incomplete, ineffective, or not credible. Instead, they relied on rough proxies (e.g., popularity) to infer S&P practices. After adoption, S&P uncertainty constrained participants' willingness to use GenAI tools, especially for high-stakes purposes, and, in some cases, contributed to discontinued use. Participants therefore called for transparency that supports decisions and actions through trustworthy information (e.g., independent evaluations) and usable interfaces (e.g., on-demand disclosure). We categorize participants' desired design practices into five dimensions to facilitate systematic future investigation into best practices. We conclude with recommendations for researchers, designers, and policymakers to improve S&P transparency in consumer-facing GenAI.

Assessing the security posture of modern computing systems typically requires the use of multiple specialized tools. These tools focus on different aspects such as configuration compliance, file integrity, and vulnerability exposure, and their outputs are often difficult to interpret collectively. This paper introduces the Unified Compliance Aggregator (UCA), a framework that integrates several open-source security tools into a single composite score representing overall system security. The proposed framework combines outputs from Lynis, OpenSCAP (STIG and CIS profiles), AIDE, Tripwire, and Nmap NSE. A normalization process converts heterogeneous outputs into a consistent 0 to 100 scale, followed by weighted aggregation. We also introduce a logarithmic scoring model for file integrity measurements to address limitations observed in prior linear approaches. Experiments were conducted on Ubuntu 22.04 across different hardening levels and environments. Results show consistent improvement in composite scores as systems are hardened, while also revealing contrasting behavior between compliance and file integrity tools. Two case studies, a basic web server and a DVWA-based system illustrate how the framework can be applied in practical scenarios.

INTRODUCTION: The proliferation of the amalgamation of IoT and edge computing has increased the demand for decentralised trust and security mechanisms capable of operating across heterogeneous and resource-limited devices. Approaches such as federated learning, Zero Trust architectures, lightweight blockchain and distributed neural models offer alternatives to centralised control. OBJECTIVES: This review examines various state-of-the-art decentralised mechanisms and evaluates their effectiveness in terms of securing IoT networks at the edge. METHODS: Thirty recent studies were analysed to compare how decentralised architectures establish trust, support secure communication and enable intrusion and anomaly detection. Frameworks, such as DFGL-LZTA, SecFedDNN and COSIER were assessed. RESULTS: Decentralised designs enhance privacy, reduce single points of failure and improve adaptive threat response, though challenges remain in scalability, efficiency and interoperability. CONCLUSION: The study identifies key considerations and future research needs for building secure and resilient trust-aware IoT edge ecosystems.

Modern AI agents routinely depend on secrets such as API keys and SSH credentials, yet the dominant deployment model still exposes those secrets directly to the agent process through environment variables, local files, or forwarding sockets. This design fails against prompt injection, tool misuse, and model-controlled exfiltration because the agent can both use and reveal the same bearer credential. We present CapSeal, a capability-sealed secret mediation architecture that replaces direct secret access with constrained invocations through a local trusted broker. CapSeal combines capability issuance, schema-constrained HTTP execution, broker-executed SSH actions, anti-replay session binding, policy evaluation, and tamper-evident audit trails. We describe a Rust prototype integrated with an MCP-facing adapter, formulate conditional security goals for non-disclosure, constrained use, replay resistance, and auditability, and define an evaluation plan spanning prompt injection, tool misuse, and SSH abuse. The resulting system reframes secret handling for agentic systems from handing the model a key to granting the model a narrowly scoped, non-exportable action capability.

Reinforcement learning is a promising approach to autonomous and adaptive security management in networked systems. However, current reinforcement learning solutions for security management are mostly limited to simulation environments and it is unclear how they generalize to operational systems. In this paper, we address this limitation by presenting CSLE: a reinforcement learning platform for autonomous security management that enables experimentation under realistic conditions. Conceptually, CSLE encompasses two systems. First, it includes an emulation system that replicates key components of the target system in a virtualized environment. We use this system to gather measurements and logs, based on which we identify a system model, such as a Markov decision process. Second, it includes a simulation system where security strategies are efficiently learned through simulations of the system model. The learned strategies are then evaluated and refined in the emulation system to close the gap between theoretical and operational performance. We demonstrate CSLE through four use cases: flow control, replication control, segmentation control, and recovery control. Through these use cases, we show that CSLE enables near-optimal security management in an environment that approximates an operational system.

There is increasing interest in integrating AI agents that invoke tools into domain-specific commercial software, where unintended tool calls can cause serious security and safety incidents. This has drawn growing research attention, and many agent security and safety benchmarks have emerged. They implicitly shape how the community approaches security and safety. Yet existing work exhibits a blind spot: it emphasizes training-based methods and neural guardrails, which reduce the likelihood of insecure or unsafe actions but cannot guarantee their prevention. It generally overlooks opportunities for deductive, symbolic guardrails grounded in standard software engineering practices, which can provide guarantees for some security and safety requirements. Our study has three parts: (1) a systematic review of 80 agent security and safety benchmarks finding that that 85% of benchmarks do not state verifiable requirements (61% provide none, and 24% give only high-level goals); (2) an applicability analysis of which security and safety requirements symbolic guardrails can and cannot enforce on $τ^2$-Bench, CAR-bench, and MedAgentBench, finding that 74% of requirements are symbolically enforceable and 95% of these need only simple, low-cost checks; and (3) an empirical evaluation of symbolic guardrails on the same three benchmarks, finding that symbolic guardrails improve security and safety without sacrificing utility, and often improve it. Our work draws attention to the potential for symbolic guardrails for AI agents, suggesting them as an overlooked but practical path toward deploying domain-specific AI agents in risk-averse commercial software. We release all codes and artifacts at https://github.com/hyn0027/agent-symbolic-guardrails.

The communication protocols and data transfer mechanisms employed by IoT devices in smart buildings and corresponding digital twin systems predominantly rely on centralized architectures. Such centralized systems are vulnerable to single points of failure, where a malfunction can disrupt operational processes. This study introduces a blockchain-based decentralized protocol to enhance the cyber resilience of IoT data transfer for digital twins and enable decentralized automation of building operations. The framework incorporates public and private blockchain technologies alongside two case studies showcasing prototypes of each system. These prototypes were validated within a real-world building environment using smart home appliances and two digital twin platforms, with their performance evaluated based on cost, scalability, data security, and privacy. The findings reveal that the Hyperledger Fabric-based system excels in terms of scalability, speed, and cost-effectiveness, while both frameworks offer advantages over traditional centralized protocols in system cyber resilience, data security, and privacy.

Large language models (LLMs) have evolved into autonomous agents that rely on open skill ecosystems (e.g., ClawHub and Skills.Rest), hosting numerous publicly reusable skills. Existing security research on these ecosystems mainly focuses on vulnerabilities within skills, such as prompt injection. However, there is a critical gap regarding skills that may be misused for harmful actions (e.g., cyber attacks, fraud and scams, privacy violations, and sexual content generation), namely harmful skills. In this paper, we present the first large-scale measurement study of harmful skills in agent ecosystems, covering 98,440 skills across two major registries. Using an LLM-driven scoring system grounded in our harmful skill taxonomy, we find that 4.93% of skills (4,858) are harmful, with ClawHub exhibiting an 8.84% harmful rate compared to 3.49% on Skills.Rest. We then construct HarmfulSkillBench, the first benchmark for evaluating agent safety against harmful skills in realistic agent contexts, comprising 200 harmful skills across 20 categories and four evaluation conditions. By evaluating six LLMs on HarmfulSkillBench, we find that presenting a harmful task through a pre-installed skill substantially lowers refusal rates across all models, with the average harm score rising from 0.27 without the skill to 0.47 with it, and further to 0.76 when the harmful intent is implicit rather than stated as an explicit user request. We responsibly disclose our findings to the affected registries and release our benchmark to support future research (see https://github.com/TrustAIRLab/HarmfulSkillBench).

As agent systems move into increasingly diverse execution settings, trajectory-level safety evaluation and diagnosis require benchmarks that evolve with them. ATBench is a diverse and realistic agent trajectory benchmark for safety evaluation and diagnosis. This report presents ATBench-Claw and ATBench-Codex, two domain-customized extensions that carry ATBench into the OpenClaw and OpenAI Codex / Codex-runtime settings. The key adaptation mechanism is to analyze each new setting, customize the three-dimensional Safety Taxonomy over risk source, failure mode, and real-world harm, and then use that customized taxonomy to define the benchmark specification consumed by the shared ATBench construction pipeline. This extensibility matters because agent frameworks remain relatively stable at the architectural level even as their concrete execution settings, tool ecosystems, and product capabilities evolve quickly. Concretely, ATBench-Claw targets OpenClaw-sensitive execution chains over tools, skills, sessions, and external actions, while ATBench-Codex targets trajectories in the OpenAI Codex / Codex-runtime setting over repositories, shells, patches, dependencies, approvals, and runtime policy boundaries. Our emphasis therefore falls on taxonomy customization, domain-specific risk coverage, and benchmark design under a shared ATBench generation framework.

Training reinforcement-learning agents for cyber defense requires an environment that reflects the operational setting: noisy, partial observations, several defenders coordinating across a network, and an adaptive adversary realized through self-play. We present NetForge RL, a multi-agent environment for this setting on procedurally generated enterprise and operational-technology (OT) networks. A red agent compromises hosts with partial observability; three zone-split blue agents defend from synthetic SIEM telemetry, Windows/Sysmon event logs encoded into dense embeddings rather than a ground-truth state vector. The environment follows the PettingZoo parallel API with fixed-shape observations and MITRE ATT&CK-mapped actions, ships five scenarios with named difficulty presets and a held-out evaluation split, and replays deterministically under a seed. A JAX backend vectorizes a reduced transition core, reaching 2.5 x 10^5 environment-steps/s at batch 4096 on CPU, as a fast surrogate for training-loop iteration. Alongside the environment we provide reference baselines (scripted, a JAX IPPO trainer, and a self-play tournament), six diagnostic probes that each measure one defensive skill, and an evaluation runner reporting 95% confidence intervals. We describe the reproducibility engineering behind the environment and include a responsible-use statement.

Instructional alignment, the match between intended cognition and enacted activity, is central to effective instruction but hard to operationalize at scale. We examine alignment in cybersecurity simulations using multimodal traces from 23 teams (76 students) across five exercise sessions. Study 1 codes objectives and team emails with Bloom's taxonomy and models the completion of key exercise tasks with generalized linear mixed models. Alignment, defined as the discrepancy between required and enacted Bloom levels, predicts success, whereas the Bloom category alone does not predict success once discrepancy is considered. Study 2 compares predictive feature families using grouped cross-validation and l1-regularized logistic regression. Text embeddings and log features outperform Bloom-only models (AUC0.74 and 0.71 vs. 0.55), and their combination performs best (Test AUC0.80), with Bloom frequencies adding little. Overall, the work offers a measure of alignment for simulations and shows that multimodal traces best forecast performance, while alignment provides interpretable diagnostic insight.

LLM agents are becoming increasingly important in the security domain, but leading systems are often closed-source, cloud-based, hard to reproduce or use with sensitive code. This creates a need for small, local models that can perform security tasks under strict resource constraints, though effective methods for developing them remain unexplored. In this paper, we address this gap by proposing a two-stage post-training recipe that turns a small local language model into a security agent. To this end, we focus on Linux privilege escalation as a representative setting to systematically study the training of local models, as the task is both automatically verifiable and requires multi-step interactive reasoning. Using an experimental setup that mitigates data leakage, we post-train a small 4B model in two stages: supervised fine-tuning on traces from procedural privilege-escalation environments, followed by reinforcement learning with verifiable rewards. On a held-out benchmark of 12 Linux privilege-escalation scenarios, supervised fine-tuning doubles the baseline success rate under a tight budget of 20 interaction rounds, and subsequent reinforcement learning training improves our model, PrivEsc-LLM 4B, to 93.3% success, behind only Claude Opus 4.7 at this budget. At the same time, the expected inference cost per successful escalation decreases by more than 80x. Our findings not only show that small local models can be adapted to complex security tasks, but also document the challenges involved, offering guidance for transferring this recipe to other settings.

Large language models (LLMs) increasingly act as autonomous agents, using tools to execute code, read and write files, and access networks, creating novel security risks. To mitigate these risks, agents are commonly deployed and evaluated in isolated "sandbox" environments, often implemented using Docker/OCI containers. We introduce SANDBOXESCAPEBENCH, an open benchmark that safely measures an LLM's capacity to break out of these sandboxes. The benchmark is implemented as an Inspect AI Capture the Flag (CTF) evaluation utilising a nested sandbox architecture with the outer layer containing the flag and no known vulnerabilities. Following a threat model of a motivated adversarial agent with shell access inside a container, SANDBOXESCAPEBENCH covers a spectrum of sandboxescape mechanisms spanning misconfiguration, privilege allocation mistakes, kernel flaws, and runtime/orchestration weaknesses. We find that, when vulnerabilities are added, LLMs are able to identify and exploit them, showing that use of evaluation like SANDBOXESCAPEBENCH is needed to ensure sandboxing continues to provide the encapsulation needed for highly-capable models.

The rapid evolution of GUI-enabled agents has rendered traditional CAPTCHAs obsolete. While previous benchmarks like OpenCaptchaWorld established a baseline for evaluating multimodal agents, recent advancements in reasoning-heavy models, such as Gemini3-Pro-High and GPT-5.2-Xhigh have effectively collapsed this security barrier, achieving pass rates as high as 90% on complex logic puzzles like "Bingo". In response, we introduce Next-Gen CAPTCHAs, a scalable defense framework designed to secure the next-generation web against the advanced agents. Unlike static datasets, our benchmark is built upon a robust data generation pipeline, allowing for large-scale and easily scalable evaluations, notably, for backend-supported types, our system is capable of generating effectively unbounded CAPTCHA instances. We exploit the persistent human-agent "Cognitive Gap" in interactive perception, memory, decision-making, and action. By engineering dynamic tasks that require adaptive intuition rather than granular planning, we re-establish a robust distinction between biological users and artificial agents, offering a scalable and diverse defense mechanism for the agentic era.

Deep Reinforcement Learning (DRL) has achieved remarkable success in domains requiring sequential decision-making, motivating its application to cybersecurity problems. However, transitioning DRL from laboratory simulations to bespoke cyber environments can introduce numerous issues. This is further exacerbated by the often adversarial, non-stationary, and partially-observable nature of most cybersecurity tasks. In this paper, we identify and systematize 11 methodological pitfalls that frequently occur in DRL for cybersecurity (DRL4Sec) literature across the stages of environment modeling, agent training, performance evaluation, and system deployment. By analyzing 66 significant DRL4Sec papers (2018-2025), we quantify the prevalence of each pitfall and find an average of over five pitfalls per paper. We demonstrate the practical impact of these pitfalls using controlled experiments in (i) autonomous cyber defense, (ii) adversarial malware creation, and (iii) web security testing environments. Finally, we provide actionable recommendations for each pitfall to support the development of more rigorous and deployable DRL-based security systems.

Large language models (LLMs) are increasingly used for hardware and firmware code generation, but existing studies primarily evaluate functional correctness while largely overlooking security. However, LLM-generated code that appears functionally sound may embed security flaws which could induce catastrophic damages after deployment. This critical research gap motivates us to design a benchmark for assessing security awareness under realistic specifications. In this work, we introduce HardSecBench, a benchmark with 924 tasks spanning Verilog Register Transfer Level (RTL) and firmware-level C, covering 76 hardware-relevant Common Weakness Enumeration (CWE) entries. Each task includes a structured specification, a secure reference implementation, and executable tests. To automate artifact synthesis, we propose a multi-agent pipeline that decouples synthesis from verification and grounds evaluation in execution evidence, enabling reliable evaluation. We evaluate diverse LLMs and find that they often satisfy functional requirements while leaving security risks. We also find that security results vary with prompting. These findings highlight pressing challenges and offer actionable insights for future advancements in LLM-assisted hardware design. Our data and code are available at https://github.com/chenqirui2002/HardSecBench.

Large multimodal model powered GUI agents are emerging as high-privilege operators on mobile platforms, entrusted to perceive screen content and inject inputs across application boundaries. While these agents aim to automate complex tasks, we demonstrate that their design introduces a fundamental conflict with Android's strict application sandboxing. We present a novel cross-application Action Rebinding attack, which allows a malicious application with zero dangerous permissions to hijack the agent's execution and perform privileged operations on behalf of the attacker. Our attack exploits the inevitable observation-action gap inherent in the agent's reasoning pipeline. A malicious app can render a benign ``contextual carrier'' to elicit a planned action, and then swap the foreground to a sensitive target application during the reasoning latency. The agent, unaware of the transition, unwittingly executes the action in the privileged context. We further advance this attack by weaponizing the agent's own task-recovery logic to create programmable, multi-step exploit loops , and introducing an Intent Alignment Strategy (IAS) that manipulates the agent's reasoning to rationalize the hijacked state. We evaluate our attack on six widely-used Android GUI agents. Our results demonstrate a 100% success rate for atomic action hijacking and the ability to orchestrate high-impact exploits, including unauthorized file deletion, SMS transmission, and app uninstallation, without the attacker holding any corresponding permissions. Furthermore, since the malicious application separates intent from capability and contains no privileged API calls, it achieves a 0% detection rate across commercial malware scanners (e.g., VirusTotal), highlighting a critical blind spot in current mobile security analysis. To access experimental logs and demonstration videos, please contact yi_qian@smail.nju.edu.cn.

Distributed Fiber Optic Sensing (DFOS) has emerged as a promising technology for long-range and real-time perimeter security in critical infrastructure monitoring. However, DFOS signals collected from different field deployments often exhibit substantial distribution shifts caused by variations in fiber installation, structural coupling, and environmental noise. These deployment-dependent changes make reliable event recognition difficult in practical perimeter security systems, especially when labeled samples from new target sites are scarce or unavailable. To address these challenges, this paper proposes DUPLE, an intelligent cross-deployment recognition framework for fiber-optic perimeter security under label-scarce target deployments. DUPLE employs statistically guided meta-learning to enhance recognition robustness across unseen deployments. Specifically, a dual-domain multi-prototype learner jointly models temporal and frequency-domain evidence to capture intra-class variability under deployment shifts. A statistical guidance network estimates sample-specific domain reliability from raw signal statistics, while a query-aware aggregation mechanism adaptively selects relevant prototypes for each test sample. Extensive experiments on two real-world cross-deployment DFOS benchmarks demonstrate that DUPLE consistently outperforms representative traditional machine learning, deep learning, domain generalization, and meta-learning baselines. Ablation, few-shot, per-deployment, and efficiency analyses further verify the effectiveness and practicality of DUPLE for reliable DFOS-based perimeter security monitoring.

Large Language Models (LLMs) are increasingly used as interfaces to information, code, and real-world services, making prompt-level security failures a practical concern. Although jailbreak attacks, defenses, datasets, and automated judgers have advanced rapidly, evaluation remains fragmented across threat models, access assumptions, cost budgets, datasets, and success criteria. This makes reported attack success rates and defense gains hard to compare. This SoK systematizes LLM prompt security across concepts, data, tooling, and measurement. We propose linked taxonomies for jailbreak attacks, defenses, and model vulnerabilities, while separating technical mechanisms from attacker and defender capabilities. We also formalize threat, access, and cost assumptions as explicit evaluation metadata. To support reproducible evaluation, we release JailbreakDB, PromptSecurity-Eval, and PromptSecurity, a modular platform that represents each experiment as a tuple of model, attack, defense, dataset, and judger. Using matched evaluations across models, attacks, defenses, and judgers, we show that access regime, native harmful-query behavior, attack cost, defense backfire, taxonomy subcategory, and judger choice all materially affect security conclusions. Together, these artifacts support reproducible, cost-aware, and taxonomy-grounded evaluation of LLM prompt security. Leaderboard: https://datasec-lab.github.io/PromptSecurityLeaderboard/. Dataset: https://huggingface.co/datasets/youbin2014/JailbreakDB. GitHub: https://github.com/datasec-lab/PromptSecurity.

Large language models (LLMs) are transforming everyday applications, yet deployment in cybersecurity lags due to a lack of high-quality, domain-specific models and training datasets. To address this gap, we present CyberPal 2.0, a family of cybersecurity-expert small language models (SLMs) ranging from 4B-20B parameters. To train CyberPal 2.0, we generate an enriched chain-of-thought cybersecurity instruction dataset built with our data enrichment and formatting pipeline, SecKnowledge 2.0, which integrates expert-in-the-loop steering of reasoning formats alongside LLM-driven multi-step grounding, yielding higher-fidelity, task-grounded reasoning traces for security tasks. Across diverse cybersecurity benchmarks, CyberPal 2.0 consistently outperforms its baselines and matches or surpasses various open and closed-source frontier models, while remaining a fraction of their size. On core cyber threat intelligence knowledge tasks, our models outperform almost all tested frontier models, ranking second only to Sec-Gemini v1. On core threat-investigation tasks, such as correlating vulnerabilities and bug tickets with weaknesses, our best 20B-parameter model outperforms GPT-4o, o1, o3-mini, and Sec-Gemini v1, ranking first, while our smallest 4B-parameter model ranks second.