Multiple Attack Surfaces

We formulate indirect prompt injection as a test-time search over a task-dependent attack surface induced by the environment, user task, and injection task. To operationalize this formulation, we introduce an agentic attacker with a dedicated search harness that performs environment reconnaissance, structured reasoning over attack strategies, and adaptive evaluation using victim-agent feedback. Across heterogeneous tasks, we find that increasing attacker test-time compute improves vulnerability discovery and exploitation, while ablations show that explicit strategy management is important for avoiding redundant search and sustaining gains at larger budgets. These results suggest that agentic security evaluations should characterize both the attacker's search procedure and compute budget, rather than treating attack success as a budget-independent property of the victim. More broadly, our findings identify the attacker's adaptive search over the system attack surfaces as an important and underexplored security risk for tool-using agents.

Large language model (LLM) agents integrated with external tools are vulnerable to indirect prompt injections embedded in environmental states. However, existing studies largely rely on manually implemented or reused environments, stochastic LLM-based tool simulation, and predefined injection locations, limiting scalable security research across broader domains. To bridge this gap, we propose ToolHazard, a scalable adversarial environment synthesis framework that reduces human engineering and supports expansion with additional seed domains and compute. Through an Environment Simulator, an Attacker Agent, and a User Simulator, ToolHazard synthesizes executable stateful environments, discovers viable injection points and generates environment-specific payloads, and constructs state-grounded long-horizon tasks. Based on ToolHazard, we build ToolHazard-Bench for stress-testing agents under complex workflows and diverse environmental attacks. Experiments reveal substantial agent vulnerabilities and show that injection timing and placement affect attack effectiveness. Moreover, ToolHazard-generated alignment data improves security on both ToolHazard-Bench and AgentDojo while preserving benign task utility.

In the era of large language models (LLMs), attackers often manipulate natural language to elicit unsafe or harmful outputs, creating a new natural language attack surface unique to LLM-based systems, where attacks directly exploit explicit linguistic cues in user prompts to bypass the safety mechanism of LLMs. However, such attacks can often be mitigated by existing safety alignment algorithms. On the other hand, human language is inherently grounded in pragmatics, necessitating typical context to interpret language, e.g., world knowledge, social norms. However, such contexts are often implicit because they are not directly expressed in human language and are not sufficiently leveraged in safety alignment, creating a fundamental mismatch between human language interpretation and safety alignment approaches. In this paper, we demonstrate that this mismatch exposes vulnerabilities in LLMs. We refer to this vulnerability as the pragmatic attack surface, which can be exploited to achieve high attack success rates. The experimental results demonstrate that our proposed approach outperforms baseline attack methods across various open-source and closed-source models by a substantial margin.

Multimodal LLM judge panels can cross-reference peers, but a quoted peer judgment may itself be untrusted. We expose source-blind anchoring as a text-level attack surface in vision-language model (VLM) panels. Quoting independent visual judgments creates large anchoring gaps (19--26 percentage points) under both self and peer framing. A matched-content, label-only control changes the broken rate by only $-0.17$pp (95% CI $[-0.68,0.35]$), showing that the self/peer label itself does not explain the effect. Under our tested construction, deliberately generated, concise wrong quotes overturn originally-correct verdicts 1.5--2.7$\times$ more often than naturally occurring wrong peer statements, with bootstrap 95% CIs excluding parity across two datasets and seven VLM judges. Because the two statement populations differ in selection and form, this ratio measures differential damage under the tested attack rather than a provenance-only causal effect. We then introduce panel-consensus verification, which cross-checks a quote against independently collected blind votes. It blocks 84.9% of fabricated attacks, cuts their net harm by 97.5%, and preserves the positive but statistically inconclusive point estimate for genuine peer information under leave-one-out re-verification. These results identify a low-cost attack surface and a concrete defense for safer multimodal collaborative evaluation.

Giving an AI agent the ability to send emails, query databases, or execute commands is useful--until the agent is tricked into doing something it shouldn't. Prompt injection, hallucinated reasoning, and unsafe tool calls form the primary attack surface for autonomous LLM agents. Existing defenses rely on software checks like system prompts or policy filters running on the same machine the attacker targets, offering no verifiable proof of execution. We introduce Niyam-AI, a framework that makes safety enforcement provable. At session start, permitted tools and constraints are locked into an Intent Contract committed via SHA-256. Every tool call is intercepted and validated by an isolated Judge model; upon passing, a zk-SNARK proof is generated via EZKL. The tool executes only after proof verification, allowing third parties to confirm enforcement without accessing Judge model weights. Evaluating Niyam-AI on 2,000 real-world scenarios from Agent-SafetyBench against NeMo Guardrails, Meta's Llama Prompt Guard 2, and OpenAI's GPT-OSS-Safeguard using 5-fold stratified cross-validation yields an F1 score of 88.5% with a 1.1% false-positive rate (bootstrap 95% CI: [85.19%, 91.88%], N=1000). McNemar's exact paired test confirms significant improvement: Niyam-AI wins 390 discordant scenarios against NeMo (vs 20 losses), 115 against Prompt Guard 2 (vs 13), and 384 against GPT-OSS-Safeguard (vs 19) with p < 0.0001 in all cases. Proof generation adds 2260.6 +/- 218.4 ms per approved action, while verification takes 53.1 +/- 11.8 ms. Niyam-AI provides a guardrail that is both highly accurate and mathematically verifiable--though this reflects a classifier adapted to Agent-SafetyBench evaluated against zero-shot baselines, a distinction discussed in Section IV.C.

Large Language Models (LLMs) are increasingly used as high-level planners in embodied multi-robot systems, enabling robots to interpret natural language instructions and coordinate executable actions. Yet, this growing reliance on LLM planners also raises security concerns. Prior work has focused mainly on individual robots, while communication risks in multi-robot collaboration remain insufficiently understood. Existing multi-robot studies are further limited to preliminary analysis under the Decentralized Multi-agent System (DMAS) architecture, so it remains unclear whether these risks persist across other common communication architectures and how attacker access settings shape their propagation. To fill this gap, we formulate two communication attacks corresponding to distinct attacker access settings: the External Entry Point Attack and the Privileged In-System Attack. We evaluate both attacks across DMAS, HMAS-1, and HMAS-2 using three LLMs and five embodied multi-robot tasks. Results show that unsafe information can turn into unsafe actions across all three architectures: DMAS reaches a 96.7% entry endorsement rate and a 100% post endorsement activation rate, HMAS-1 reaches a 97.8% unsafe action success rate, and HMAS-2 triggers 88.3% of task defined unsafe action slots. To mitigate risks from trusted information flow, we introduce the Claim Provenance and Verification (CPV) Gate, which verifies communicated claims before downstream reuse and reduces the violation rate from 70.0% to 36.6%.

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.

Ultraconstructive Model Theory (UCMT) replaces idealized satisfaction, at finite compu- tational scale, by bounded adversarial survival. A finite partial structure is tested by an Opponent (Devil) drawing legal challenges from a bounded attack surface, repaired by a Builder (God) through legal replies, and certified by a symbolic Judge

Large language models (LLMs) used as listwise rerankers in recommendation systems suffer from position bias when serializing candidate sets into prompts. We show this order sensitivity creates an exploitable attack surface: an attacker can promote a label-0 target into the top-$k$ solely by reordering candidates, without changing item content, labels, or model parameters. We introduce $\mathrm{promo}@k$ to quantify this vulnerability, measuring the fraction of label-0 targets that can be elevated into top-$k$ rankings via permutation. Evaluating across three domains (MovieLens, Amazon Books, and Amazon Fashion), $\mathrm{promo}@5$ reaches up to 0.57 at an attack budget of $R$ = 50 orderings. Furthermore, ordinary permutation stability predicts vulnerability without running the attack. While a bidirectional T5 encoder scorer reduces exposure, permutation-consistency regularization and architectural invariance effectively mitigate it. Pointwise scoring avoids the bias issue but degrades ranking quality. These results demonstrate that input candidate order in listwise LLM reranking is a security-relevant attack vector. Code and data are available at https://github.com/geoz-lab/position_bias_attack.

Large language models increasingly use search tools to retrieve up-to-date information, introducing a new attack surface in which retrieved documents can be manipulated. This risk is amplified by the development of generative engine optimization, which can make selected content more likely to be retrieved, cited, and adopted by models. Existing fact-verification benchmarks and evaluation frameworks do not provide the controlled evidence environments needed to assess robustness against GEO poisoning. We therefore propose GPE, which consists of a multi-domain fact-verification benchmark and an evaluation framework for controlling evidence sources and poisoning ratios. Experiments across multiple verification methods and poisoning attacks demonstrate that GPE exposes robustness degradation and efficiency trade-offs that cannot be observed through clean evaluation alone, confirming the need to evaluate fact verification under adversarial evidence environments.

LLM-agent defenses are typically evaluated one session at a time. In deployment, however, attacks can be distributed across independent agents, teams, and runtimes, leaving each local guardrail with only a sparse fragment. We formalize cross-agent asynchronous campaign attribution: linking sessions from the same latent adversarial campaign without shared runtime state, test-time campaign labels, or attacker identity oracles. We introduce Asynchronous Attribution Fingerprint Vectors ($A^2FV$), a lightweight proxy-side reference protocol for scoring pairwise campaign similarity from proxy-observable tool-use, timing, and prompt residue. We also construct SCD-v1, a controlled persona-matched benchmark with benign traffic, isolated attacks, multi-session campaigns, matched non-oracle evasion, and leakage audits. On SCD-v1, $A^2FV$ achieves 0.82 pairwise AUC for campaign linking, while score-only adaptations of per-session detectors and chunked LLM judges remain near chance under the same task. The strongest fixed signal is carried by structural and stylometric residue, while timing is retained as a diagnostic channel for richer proxy traces. Crossed-style controls show that the signal is partly style-sensitive but not reducible to style alone. Static and dimension-aware non-oracle stress tests further show that pairwise separability persists under controlled evasion. These results establish cross-agent campaign attribution as a distinct evaluation layer for securing LLM agents in the wild.

In the digital era, Portable Document Format (PDF) is one of the most widely used file formats for storing and exchanging digital documents due to its platform independence and rich functionality. However, these same capabilities have also made PDF files an attractive attack vector for cyberattackers, who embed malicious code within seemingly legitimate documents to compromise target systems. This paper presents a novel interpretable Tsetlin Machine (TM)-based framework for PDF malware detection. The proposed framework extracts salient features from PDF documents through static analysis without executing the files and employs rule-based learning to accurately classify benign and malicious PDF documents. Numerical evaluation on the RIT-PDFMal-2026 dataset demonstrates that the proposed framework achieves competitive performance, attaining an accuracy of 98.02% compared with several ML classifiers and existing methods. Moreover, the proposed framework provides intrinsic interpretability by transparently explaining its classification decisions. The combination of competitive detection performance, computational efficiency, and intrinsic interpretability makes the proposed framework a promising solution for practical PDF malware detection.

Generative models have recently seen rapid adoption in End-to-End (E2E) autonomous driving (AD), with diffusion-based denoising and vocabulary-based retrieval becoming the dominant trajectory-decoding paradigms. Despite their architectural diversity, current generative AD planners share a common inference pattern: a fixed set of candidate trajectories (anchors, vocabulary entries, or proposal queries) is scored by one or more learned heads conditioned on the Bird's-Eye-View (BEV) features, and the highest-scored candidate is returned as the final trajectory. Under this design, the scoring head is the only barrier between perception and the motion command, and its decision margins between competing candidates are often small. We introduce \textsc{Derail}, an adversarial framework that exploits this scoring-head attack surface. Evaluated on various generative planners, \textsc{Derail} flips the trajectory selection from a safe to an unsafe candidate, with score drops of $39$--$80\%$ and collision rates of up to $50\%$, consistently outperforming generic loss-maximization and feature-divergence attacks. Our analysis suggests that safety-violating objectives govern attack effectiveness against generative AD planners, and that the scoring-head inference pattern itself is a recurring attack surface worth explicit defensive consideration.

Agentic AI systems powered by large language models (LLMs) are rapidly evolving into autonomous decision-making systems, exposing attack vectors beyond those of traditional LLM vulnerabilities. Existing security evaluations are often tied to specific implementations or domains, limiting unified comparison across heterogeneous systems. To address this gap, we introduce RIFT-Bench, a representation-driven methodology for dynamic red-teaming that enables unified evaluations across diverse agentic architectures. Building on a novel hierarchical representation, RIFT-Bench operates in two automated phases: Discovery, which extracts system structure, and Scanning, which executes adaptive adversarial attacks. It directly evaluates the examined system using 105 adaptive adversarial probes spanning diverse attack vectors and objectives. We demonstrate the effectiveness of the proposed evaluation pipeline across 45 agentic systems spanning a diverse range of implementations, showing that the approach generalizes effectively to heterogeneous agentic architectures. Beyond systems and attacks, RIFT-Bench also supports direct evaluation of mitigation strategies. These key capabilities make RIFT-Bench a scalable foundation for security evaluation of agentic AI systems in practice. Infrastructure code and benchmark artifacts are available at https://tinyurl.com/RIFTBench.

Self-evolving LLM agent systems, which autonomously update their model parameters, memory, tools, and architectures, introduce a qualitatively new threat landscape in which adversarial influences become permanently encoded, self-amplify across generations, and propagate through populations without sustained attacker access. We present a systematic security and privacy analysis organized around the Module-Lifecycle Attack Surface (MLAS) matrix, which decomposes the attack surface into five functional modules (Brain, Cognitive Resource, Execution, Self-Design, Collective) $\times$ five lifecycle stages (Bootstrap, Propose, Evaluate, Commit, Serve). Analysis of the resulting 25 cells reveals that 17 face critical threats for which no effective partial mitigation. We identify seven cross-cutting amplification effects that interact synergistically and cannot be addressed by securing individual modules in isolation. Comparative case studies of two open-source frameworks demonstrate that evolution-native design activates $3.5\times$ more attack surface cells and achieves a 100% attack persistence rate (40/40 payloads across all CIA+Privacy categories), while co-located security scanners block only 2.5% of attacks. Our findings establish that self-evolution converts every known attack category from session-bounded to lineage-persistent, gives rise to entirely new attack classes, and renders static defenses structurally inadequate, motivating evolution-aware security frameworks and formal verification for self-modifying systems.

Multi-stage cyberattacks span system, network, and browser logs. Detecting them requires correlating events across all three sources. Machine learning methods can learn these cross-source patterns, but they need labeled multi-source data. Existing public datasets fall short. Network-only datasets such as CICIDS and UNSW-NB15 miss host and browser activity. Host-focused datasets such as LMDG and CICAPT-IIoT lack browser telemetry. ATLAS includes all three sources but labels events only as malicious or benign, without MITRE Adversarial Tactics, Techniques, and Common Knowledge (ATT&CK) technique granularity. No public dataset combines all three sources with per-entry ATT&CK technique labels. We close the gap by building a multi-source log dataset of 870 sessions (70 attack, 800 benign) and approximately 2.3 million events. We captured system, network, and browser activity simultaneously on Windows endpoints. We labeled malicious events with ATT&CK technique IDs, covering 12 tactics and 53 techniques. We generated all attack data using real tools, including Remote Access Trojan (RAT), Command and Control (C2) tunnels, and cloud exfiltration. To demonstrate learnability, we fine-tuned three Small Language Models (SLMs) (Qwen2.5-1.5B, Llama-3.2-3B, Phi-4-Mini) using Low-Rank Adaptation (LoRA). We compared each against its base variant across ten metrics on two tasks: chunk classification and ATT&CK technique identification. Fine-tuning improved every model on every metric. Chunk classification accuracy rose from approximately 8% in the base variants to between 90% and 97% after fine-tuning. Technique identification remained challenging, with the best exact-match accuracy at 42%, although high partial-match scores show the models captured most of the underlying reasoning.

Agents increasingly access large language models (LLMs) through API routers. A router terminates the client's transport-layer security session and opens a separate upstream session, so it holds the full interaction in plaintext. This makes the router an application-layer man-in-the-middle: it can rewrite agent tool calls, swap dependencies for typosquatted packages, trigger attacks only under audit-evading conditions, and passively exfiltrate secrets. Existing client-side defenses are evadable. We propose AEGIS, a provider-transparent attested API router whose data path is a client-verified faithful passthrough. AEGISconfines plaintext handling to a small hardware-enclave component while leaving authentication, scheduling, accounting, and management on the untrusted host. The client verifies the enclave before releasing plaintext. The host can neither read nor alter the interaction, and plaintext leaves only toward destinations fixed by the measured image. We show that all four malicious-router attack classes succeed against a plaintext-access baseline and are blocked by AEGIS, including adaptive tests against the same boundary. The trusted path is $851$ lines, carries three provider-native APIs without conversion, and completes every request under real-provider workload and concurrency. In a seeded audit pilot, two commodity coding agents find eight and ten of ten planted invariant violations. The local relay overhead is about six milliseconds per request.

Large language model (LLM) agents increasingly rely on long-term memory to support complex task execution, user personalization, and domain adaptation. Meanwhile, emerging access-control mechanisms for LLM agents are being explored to block policy-violating requests and prevent misuse. We reveal a novel attack surface arising from agent memory operations: prohibited content that would trigger access control can be fragmented across interactions, stored in long-term memory in benign-appearing form, and later reconstructed through memory retrieval without appearing explicitly in the final user query. We propose FragFuse, the first attack that enables unprivileged users to bypass agent access control by exploiting this temporal channel introduced by long-term memory. FragFuse operates in three stages: (1) identifying rejection-responsive fragments via black-box adaptive querying with fragment masking; (2) injecting these fragments into memory using marker carrier queries; and (3) retrieving and fusing the stored fragments through a follow-up attack query. Although FragFuse can be instantiated manually for individual agents, we further develop a surrogate-based optimization scheme that tunes fusion instructions and marker designs, enabling automated attack generation without violating the attacker's threat-model assumptions. We evaluate FragFuse across four representative agent settings and task domains, covering three state-of-the-art agent access-control mechanisms. FragFuse achieves an average bypass success rate of 86.3% and an average end-to-end harmful task success rate of 41.1% across all settings, with only 4.4% average task-success degradation compared with configurations without access control. We also show that alternative defenses, including state-of-the-art prompt-injection detectors and perplexity detectors, do not effectively address this attack.

A vision encoder compresses image pixels into semantic embeddings, implicitly acting as a privacy boundary by preserving semantic content while attenuating pixel-local detail required for exact text recovery. Encoder-free vision-language models (VLMs) remove this boundary by routing image patches directly into the language-model token stream, thereby exposing an architectural privacy attack surface: intermediate visual tokens become a pre-output side channel. Under a token-access adversary, decoders invert visual-token streams from two encoder-free VLMs, Gemma4 and Fuyu, recovering recognizable image structure and readable held-out access codes, whereas matched encoder-based controls localize target regions but recover no exact strings. Within-model ablations show that the operative factor is spatial sampling fidelity of the visual-token grid, especially character-direction sampling density, rather than token or value count. The leakage is not limited to exported tokens: Gemma4 layer-0 key-value cache tensors are directly invertible, placing the side channel within KV caches commonly persisted by production serving stacks for decoding efficiency. The attack survives clutter, realistic document degradation, and zero-shot transfer to public document images, and it resists value-level defenses such as additive noise and quantization. Effective mitigation must therefore reduce spatial sampling, making removal of the vision encoder a first-class privacy decision in VLM deployment.

Modern agentic systems transform LLMs from session-bounded assistants into stateful systems that persist and evolve shared world state across sessions through memories, filesystems, tools, and other long-lived contextual artifacts. This shift fundamentally expands the attack surface of prompt injection. However, prior works on prompt injection have largely focused on model-level threats within a single session, overlooking how cross-session persistent system state fundamentally changes the system-level risk of agentic systems. Inspired by stored cross-site scripting in web systems, we introduce cross-session stored prompt injection, where a successful injection can persist within agentic system state and silently influence future executions long after the original attacker interaction has ended. To systematically study this threat, we formalize stored prompt injection and develop a taxonomy of how adversarial content persists and affects agentic systems across sessions. We further develop a benchmark and sandbox toolkit to evaluate the risks of stored prompt injection, enabling quantitative analysis of attack success across different models, attack goals, and persistence channels. Our findings highlight that persistence transforms prompt injection from an ephemeral model-level threat into a long-lived system-level vulnerability embedded within agent execution state. We hope this work draws broader attention to this emerging threat and motivates the community to systematically study and mitigate system risks arising from persistence in agentic systems.

ReAct agents that interleave chain-of-thought reasoning with tool calls are increasingly deployed for real tasks such as scheduling, file retrieval, and data access. Their tool observation loop creates a direct attack surface: an adversary who controls any tool's return value can embed instructions that redirect the agent away from the user's goal, a threat known as indirect prompt injection. Existing benchmarks evaluate attack success rate (ASR) at a fixed injection position under fixed conditions, leaving three risk dimensions unexplored: where in the tool sequence the payload appears (injection depth), what rhetorical register it uses (framing), and how many turns the agent is permitted (turn cap). We conduct four controlled studies on 20 scenarios spanning five attack categories, totalling 460 trials against GPT-4o-mini and Claude Haiku at a combined API cost under 0.36 USD. Study 1 shows that ASR against GPT-4o-mini decays from 60% at depth 1 to 0% at depths 4 and 5 (Cramer's V = 0.58, p < 0.001; restricted to within-sequence depths 1-3: V = 0.47, p = 0.0013), driven by model resistance at depth 1 and task completion before payload encounter at deeper positions. Study 2 replicates the depth experiment on Claude Haiku, which achieves 0% ASR at every depth through a combination of conservative tool invocation and genuine instruction resistance. Study 3 shows that framing modulates ASR between 25% (neutral) and 75% (persona) at depth 1, a 50-percentage-point range that does not reach statistical significance at N = 20 per condition. Study 4 confirms that ASR is stable across turn caps of 3, 5, and 7, indicating the turn budget is not a risk factor in this setting. Our results establish injection depth as the dominant variable and show that sanitising only the first tool observation captures 67% of measured injection successes.

Tool-augmented LLM agents are vulnerable to prompt injection: a third party who controls part of the agent's context can plant instructions that the agent then executes as if they came from the user. Current evaluations report a single attack success rate per model on one channel, the tool output and treat that number as the model's vulnerability. But tool descriptions, which the agent reads at every turn before any tool is called, are themselves an injection surface that the attacker can choose instead. We hold the injection payload byte-identical and deliver it through both surfaces across 13 LLMs from six families and four task suites. The same bytes invert in success rate across models: GPT-4.1 is 96 percent vulnerable on tool outputs but only 4 percent on tool descriptions, while GEMINI-3-FLASH shows the mirror pattern at 20 percent and 98 percent. A variance decomposition over 6,830 attempts attributes 0 percent of the variation in attack outcomes to the surface alone, while the model-surface interaction accounts for 16.7 percent. Vulnerability is a property of the pairing, not the channel. The Adaptive Attack Rate, defined as the per-cell maximum over surfaces, exceeds the strongest fixed-surface baseline by +9.1 percentage points on average. Standard prompt-level defenses inherit the same blindspot, reducing tool-output ASR to 10-18 percent while leaving the description channel above 54 percent. Both attack and defense evaluation must report per-surface vulnerability.

We demonstrate an attack on Introspection Adapters (Shenoy et al., 2026).

LLM-driven agents are capable of selecting external tools to complete users' tasks. However, attackers could compromise such process, steering agents toward inappropriate/wrong tools and enabling malicious actions. Most existing attacks primarily manipulate the tool metadata, which is easily detectable by auditing and may lose effectiveness as modern agents increasingly adopt memory modules to refine tool selection policies through accumulated experience. This paper proposes MemMorph, the first attack that bias tool selection by poisoning the agent's long-term memory. Rather than explicitly dictating the tool invocation decision, MemMorph injects a small number of crafted records that are disguised as technical facts, incident reports, and operational policies. These poisoned records reshape the agent's contextual perception and decision-making process, leading it to autonomously infer and select the tool preferred by the attacker. Experiments across 3 benchmarks, 10 agent backbones, and 3 memory-module implementations show that MemMorph achieves up to 85.9% attack success rate with only three injected records, outperforming the strongest baseline by up to 25% while retaining potency under 3 representative defenses. Our findings expose long-term memory as a critical and under-explored attack surface in tool-augmented agents, urging the development of memory-level integrity safeguards.

Large language models are increasingly augmented with persistent memory, allowing assistants to store user-specific information across sessions for personalization and continuity. This statefulness introduces a new security risk: adversarial content can corrupt what an assistant remembers and thereby influence future interactions. We propose and study sleeper memory poisoning, a delayed attack in which an adversary manipulates external context, such as a document, webpage, or repository, to cause the assistant to store a fabricated memory about the user. Unlike conventional prompt injection, the attack can remain dormant and re-emerge across multiple later conversations. We evaluate the full attack pipeline: whether poisoned memories are written, later retrieved, and ultimately used to steer the following conversations. Across stateful LLM assistants, poisoned memories were added up to 99.8% on GPT-5.5 and 95% on Kimi-K2.6. Crucially, among successful retrievals, poisoned memories cause attacker-intended agentic actions in 60-89% of evaluations across models. These results show that persistent memory can act as a long-term attack surface across multiple future conversations.

Web-browsing AI agents are increasingly deployed in enterprise settings under strict whitelists of approved domains, yet adversaries can still influence them by embedding hidden instructions in the HTML pages those domains serve. Existing red-teaming resources fall short of this scenario: prompt-injection benchmarks ship pre-built adversarial pages that whitelisted agents cannot reach, and generic LLM scanners probe the model API rather than its retrieved content. We present IPI-proxy, an open-source toolkit for red-teaming web-browsing agents against indirect prompt injection (IPI). At its core is an intercepting proxy that rewrites real HTTP responses from whitelisted domains in flight, embedding payloads drawn from a unified library of 820 deduplicated attack strings extracted from six published benchmarks (BIPIA, InjecAgent, AgentDojo, Tensor Trust, WASP, and LLMail-Inject). A YAML-driven test harness independently parameterizes the payload set, the embedding technique (HTML comment, invisible CSS, or LLM-generated semantic prose), and the HTML insertion point (6 locations from \icode{head_meta} to \icode{script_comment}), enabling parameter-sweep evaluation without mock pages or sandboxed environments. A companion exfiltration tracker logs successful callbacks. This paper describes the threat model, situates IPI-proxy among contemporary IPI benchmarks and red-teaming tools, and details its architecture, design decisions, and configuration interface. By bridging static benchmarks and live deployment, IPI-proxy gives AI security teams a reproducible substrate for measuring and hardening web-browsing agents against indirect prompt injection on the same retrieval surface attackers exploit in production.

AI pentesting agents are increasingly credible as offensive security systems, but current benchmarks still provide limited guidance on which will perform best in real-world targets. Existing evaluation protocols assess and optimize for predefined goals such as capture-the-flag, remote code execution, exploit reproduction, or trajectory similarity, in simplified or narrow settings. These tools are valuable for measuring bounded capabilities, yet they do not adequately capture the complexity, open-ended exploration, and strategic decision-making required in realistic pentesting. In this paper, we present a practical evaluation protocol that shifts assessment from task completion to validated vulnerability discovery, allowing evaluation in sufficiently complex targets spanning multiple attack surfaces and vulnerability classes. The protocol combines structured ground-truth with LLM-based semantic matching to identify vulnerabilities, bipartite resolution to score findings under realistic ambiguity, continuous ground-truth maintenance, repeated and cumulative evaluation of stochastic agents, efficiency metrics, and reduced-suite selection for sustainable experimentation. This protocol extends the state of the art by enabling a more realistic, operationally informative comparison of AI pentesting agents. To enable reproducibility, we also release expert-annotated ground truth and code for the proposed evaluation protocol: https://github.com/ethiack/ethibench.

Modern machine learning deployments increasingly compose specialized models into dynamic inference pipelines, where upstream components produce intermediate predictions that determine the workload and inputs of downstream components. The cost of processing an input is therefore not determined by any single model, but by two coupled factors: the per-inference cost of each invoked component and its workload volume. Because these pipelines run under hard real-time constraints, efficiency is a fundamental requirement for system availability. We show that this structure creates an efficiency-attack surface that existing methods targeting single models cannot exploit: on identical inputs and budgets, path-aware targeting inflates FLOPs by $2,407\times$ while the strongest single-model baseline achieves $117\times$ -- a $20\times$ gap attributable entirely to where the attack is directed. We formalize this as the adversarial path-selection problem and present AESOP, a framework combining vulnerability-guided path ranking with adaptive loss weighting. We evaluate AESOP on five pipelines plus a production-realistic deployment variant with batching, bounded buffering, and confidence-threshold defenses. AESOP achieves up to $2,407\times$ FLOPs and $419\times$ latency inflation in white-box setting and 58$\times$ FLOPs / 17$\times$ latency in gray-box settings. Under system-level defenses, the attack is not neutralized but redirected: pipelines are forced to choose between throughput collapse ($0.578 \to 0.006$ input/s) and $96.7\%$ data loss to sustain throughput.

The rapid expansion of the Internet of Things (IoT) and Industrial IoT (IIoT) has created a massive, heterogeneous attack surface that challenges traditional network security mechanisms. While Federated Learning (FL) offers a privacy-preserving alternative to centralized Intrusion Detection Systems (IDS), standard approaches struggle to generalize across diverse device behaviors and typically fail to utilize the vast amounts of unlabeled data present in realistic edge environments. To bridge these gaps, we propose CLAD, a holistic framework that seamlessly incorporates Clustered Federated Learning (CFL) with a novel Dual-Mode Micro-Architecture ($\text{DM}^2\text{A}$). This unified approach simultaneously tackles the two primary bottlenecks of IoT security: device heterogeneity and label scarcity. The $\text{DM}^2\text{A}$ component features a shared encoder followed by two branches, enabling joint unsupervised anomaly detection and supervised attack classification; this allows the framework to harvest intelligence from both labeled and unlabeled clients. Concurrently, the clustering component dynamically groups devices with congruent traffic patterns, preventing global model divergence. By carefully combining these elements, CLAD ensures that no data is discarded and distinct operational patterns are preserved. Extensive evaluations demonstrate that this integrated approach significantly outperforms state-of-the-art baselines, achieving a 30% relative improvement in detection performance in scenarios with 80% unlabeled clients, with only half the communication cost.

Memory systems enable otherwise-stateless LLM agents to persist user information across sessions, but also introduce a new attack surface. We characterize the Trojan Hippo attack, a class of persistent memory attacks that operates in a more realistic threat model than prior memory poisoning work: the attacker plants a dormant payload into an agent's long-term memory via a single untrusted tool call (e.g., a crafted email), which activates only when the user later discusses sensitive topics such as finance, health, or identity, and exfiltrates high-value personal data to the attacker. While anecdotal demonstrations of such attacks have appeared against deployed systems, no prior work systematically evaluates them across heterogeneous memory architectures and defenses. We introduce a dynamic evaluation framework comprising two components: (1) an OpenEvolve-based adaptive red-teaming benchmark that stress-tests defenses and memory backends against continuously refined attacks, and (2) the first capability-aware security/utility analysis for persistent memory systems, enabling principled reasoning about defense deployment across different usage profiles. Instantiated on an email assistant across four memory backends (explicit tool memory, agentic memory, RAG, and sliding-window context), Trojan Hippo achieves up to 85-100% ASR against current frontier models from OpenAI and Google, with planted memories successfully activating even after 100 benign sessions. We evaluate four memory-system defenses inspired by basic security principles, finding they substantially reduce attack success rates (to as low as 0-5%), though at utility costs that vary widely with task requirements. Because of this substantial security-utility tradeoff, the effective real-world deployment of defenses remains an open challenge, which our evaluation framework is specifically designed to address.

The prevalence of biometric authentication has been on the rise due to its ease of use and elimination of weak passwords. To date, most biometric authentication systems have been designed for on-device authentication of the device owner (e.g., smartphones and laptops). Recently, biometric authentication systems have started to emerge that are designed to authenticate users against cloud databases storing representations of biometrics for large numbers of users (potentially millions), such as those facilitating biometric payments. However, the use of a large cloud database introduces a significant attack vector, as a breach of the database could lead to the compromise of all enrolled users' sensitive biometric data. Indeed, all such existing systems either do not adequately protect against such a breach, or are impractical to deploy and use due to their high computational overhead. In this work, we present a new biometric authentication system that provides provable security guarantees against data breaches, while remaining scalable and performant. To do so, we marry artificial intelligence with advanced cryptographic techniques in a novel fashion, providing several optimizations along the way. Our work is the first to show that real-world scalable privacy-preserving biometric authentication without auxiliary identifiers is feasible, and we believe that it will spur widespread industrial adoption and further research in this area.

Agentic AI systems introduce a security surface that is qualitatively different from that of stateless LLMs. They persist memory, invoke external tools, coordinate with peer agents, and operate across sessions, allowing attacks to emerge not only at the prompt interface but also through architectural state, delegated authority, and long-horizon interactions. Existing security taxonomies, however, primarily organize threats by attack type, such as prompt injection or jailbreaking, and therefore obscure where in the agentic stack a threat arises and over what timescale it manifests. We propose the Layered Attack Surface Model (\lasm), a structural taxonomy for agentic AI security. \lasm decomposes the agentic stack into seven layers -- Foundation, Cognitive, Memory, Tool Execution, Multi-Agent Coordination, Ecosystem, and Governance -- and augments them with a four-class temporality axis covering instantaneous, session-persistent, cross-session cumulative, and sub-session-stack threats. We use this 7$\times$4 framework to analyze 116 papers from 2021--2026. The resulting map reveals that the upper layers of the agentic stack remain sharply under-explored, especially for long-horizon and stack-propagating threats; multiple documented attack regions have no corresponding defenses; and current benchmarks provide no coverage for cross-session or sub-session-stack failure modes. We further derive a cross-layer defense taxonomy, defense recipes for canonical attack classes, and a dependency DAG that separates near-term engineering gaps from fundamental research challenges. We release the per-paper coding, robustness scripts, and a reference Agent Bill of Materials schema to support reproducible analysis.

Safety-oriented instruction-following is supposed to keep LLM-controlled robots safe. We show it also creates an availability attack surface. By injecting short safety-plausible phrases (1-5 tokens) into a robots audio channel, an adversary can trigger the models safety reasoning to halt or disrupt execution without jailbreaking the model or overriding its policy. In the embodied setting, this is a semantic denial-of-service attack: the agent stops because the injected signal looks like a legitimate alert. Across four vision-language models, seven prompt-level defenses, three deployment modes, and single- and multi-injection settings, we find that prompt-only defenses trade off attack suppression against genuine hazard response. The strongest defenses reduce hard-stop attack success on some models, but defenses change the form of disruption, not its fact: suppressed hard stops re-emerge as acknowledge loops and false alerts, which we measure with Disruption Success Rate (DSR). We further find that injection variety is consistently more effective than repeating the same phrase, suggesting that models treat diverse safety cues as corroborating evidence. The practical implication is architectural rather than prompt-level: systems that route unauthenticated audio text directly into the LLM create an avoidable security dependency between safety monitoring and action selection.

Aligned large language models (LLMs) remain vulnerable to adversarial manipulation, and their reliance on web-scale pretraining creates a subtle but consequential attack surface. We study Stealth Pretraining Seeding (SPS), a threat model in which adversaries distribute small amounts of poisoned content across stealth websites, increasing the likelihood that such material is absorbed into future training corpora derived from sources such as Common Crawl. Because each individual payload is tiny, diffuse, and superficially benign, the attack is difficult to detect during dataset construction or filtering. The result is a latent form of poisoning that remains largely invisible under standard evaluation, yet can later be activated by a precise trigger such as <00TRIGGER00>. We call this attack PermaFrost, reflecting its latent and reactivatable nature. We study it through PermaFrost-Attack, a controlled framework for latent conceptual poisoning, together with three geometric diagnostics: Thermodynamic Length, Spectral Curvature, and the Infection Traceback Graph. Across multiple model families and scales, we show that this controlled SPS proxy can induce persistent unsafe behavior that often remains hidden under standard evaluation. Our results identify SPS as a practical and underappreciated threat to future foundation models. This paper introduces a novel geometric diagnostic lens for systematically examining latent model behavior, providing a principled foundation for detecting, characterizing, and understanding vulnerabilities that may remain invisible under standard evaluation.

Tool-integrated agents are deployed on the premise that external tools ground their outputs in reality. Yet this very reliance creates a critical attack surface. Current evaluations benchmark capability in benign settings, asking "can the agent use tools correctly" but never "what if the tools lie". We identify this Trust Gap: agents are evaluated for performance, not for skepticism. We formalize this vulnerability as Adversarial Environmental Injection (AEI), a threat model where adversaries compromise tool outputs to deceive agents. AEI constitutes environmental deception: constructing a "fake world" of poisoned search results and fabricated reference networks around unsuspecting agents. We operationalize this via POTEMKIN, a Model Context Protocol (MCP)-compatible harness for plug-and-play robustness testing. We identify two orthogonal attack surfaces: The Illusion (breadth attacks) poison retrieval to induce epistemic drift toward false beliefs, while The Maze (depth attacks) exploit structural traps to cause policy collapse into infinite loops. Across 11,000+ runs on five frontier agents, we find a stark robustness gap: resistance to one attack often increases vulnerability to the other, demonstrating that epistemic and navigational robustness are distinct capabilities.