arXiv subjects

Sahar Abdelnabi

Publications and source records attributed to Sahar Abdelnabi.

At least 19 recordsLinked to original sources

arXiv2026

Detecting Multi-Agent Collusion Through Multi-Agent Interpretability

As LLM agents are increasingly deployed in multi-agent systems, they introduce risks of covert coordination that may evade standard forms of human oversight. While linear probes on model activations have shown promise for detecting deception in single-agent settings, collusion is inherently a multi-agent phenomenon, and the use of internal representations for detecting collusion between agents remains unexplored. We introduce NARCBench, a benchmark for evaluating collusion detection under environment distribution shift, and propose five probing techniques that aggregate per-agent deception scores to classify scenarios at the group level, evaluated across four open-weight models (Qwen3-32B, Llama-3.1-70B, DeepSeek-R1 32B, GPT-OSS-20B) and six probe architectures. We frame this as a distributed anomaly detection problem, identifying three collusion signatures that map onto distinct anomaly types and detection paradigms. Every model reaches 1.00 AUROC in-distribution; on our strongest model (Llama-3.1-70B), our five probing techniques achieve 0.73 to 0.93 AUROC when transferred zero-shot to structurally different multi-agent scenarios and 0.99 to 1.00 on a steganographic blackjack card-counting task, with detection performance scaling with model capability. We find that no single probing technique dominates across all collusion types, consistent with the framework's prediction that different anomaly types require different detection paradigms. This work takes a step toward multi-agent interpretability: extending white-box inspection from single models to multi-agent contexts, where detection requires aggregating signals across agents. These results suggest that model internals provide a complementary signal to text-level monitoring for detecting multi-agent collusion. Code and data available at https://github.com/aaronrose227/narcbench.

cs.AI↗

arXiv2026

FIGS: Evaluating Multi-Turn Sycophancy Without Penalizing Empathy

Large language models frequently fail to balance staying truthful with being supportive. They often exhibit sycophancy in responses to users, agreeing with false claims, offering unwarranted flattery, and giving advice skewed toward users' expressed views. In reality, sycophancy rarely happens in a single exchange; it may emerge organically as users repeatedly insist or subtly steer the dialogue over time. Current evaluations, however, rely on rigid, single-turn tests or fixed scripts that fail to capture these natural dynamics. Furthermore, these benchmarks often mistake showing basic empathy for yielding, penalizing models for acknowledging a user's feeling. This view may drive future models to over-correct into cold, dismissive rigidity. To address this gap, we introduce FIGS (Factual Integrity and Grounded Support), a dual-axis evaluation framework built around extended, realistic dialogue. We use an adaptive 10-turn conversational simulator that dynamically challenges the target model, reflecting how users repeat requests, push back, or steer a conversation toward a preferred answer. To accurately evaluate these trajectories, we apply a taxonomy that strictly separates Sycophancy (whether the model holds firm to the truth and keeps its praise proportional) from Calibrated Validation (showing empathetic understanding of the user's feelings without overdoing it). We release our complete testing environment, including 500 diverse multi-turn scenarios and an automated judge. Our evaluation of leading models reveals a consistent trade-off: over the course of a sustained interaction, current systems either slowly drift to sycophancy or over-correct into robotic detachment. This demonstrates that balancing honesty with appropriate support throughout a natural conversation remains a critical, unsolved challenge.

cs.AI↗

arXiv2026

Decomposing and Measuring Evaluation Awareness

Frontier language models sometimes recognize that they are under evaluation and adjust their behavior which can undermine validity of benchmark results. Yet the field studies it without a shared foundation, conflating flaws of the evaluation with capabilities of the model, and detection with behavioral response. We ground evaluation awareness in social psychology, decomposing it into an environment component and a model component that separates recognition from propensity. We operationalize the environment component through eight categorized trigger factors, such as placeholder entities and grading-style output formats, and study recognition and behavior through chain-of-thought monitoring. Across nine frontier models and four benchmarks, recognition rates depend on the specific pairing of model and benchmark. Recognition rarely associates with behavioral change, and when it does, the direction depends on the type of evaluation perceived. Models are also more sensitive to safety than capability evaluations, placing safety benchmark validity at greater risk. To study which factors each model is sensitive to and how they interact, we propose \textbf{EvalAwareBench}, a factor-controlled benchmark of 100 paired safety-capability tasks where each of the eight factors can be independently toggled, varying evaluative signals while holding the underlying request fixed. Through EvalAwareBench, we find that no single factor uniformly affects all models, but stacking factors progressively raises evaluation awareness across all of them. Our framework and EvalAwareBench provide the tools to measure, attribute, and mitigate evaluation awareness, building the foundation for future solutions.

cs.LG↗

arXiv2026

SEABench: Benchmarking Endogenous Misalignment In Self-Evolving Agents

Self-evolving LLM agents have gained prominence for their ability to improve after deployment by modifying their harness, including their controller instructions, memory management protocols, and reusable tools and skills, in response to user and environment feedback. However, locally useful updates may persist into later tasks where they produce unsafe behavior, even without direct adversarial influence. To study this risk, we introduce SEABench, a benchmark for studying endogenous misalignment arising from agent self-evolution, with 48 longitudinal task sequences that span multiple evolution surfaces, task domains, and harm types in a rich personal-assistant environment. To account for the stochasticity inherent in agentic operations, we provide an adaptive trajectory discovery pipeline that probes for failures while preserving original task intent and supports causal attribution through paired non-evolving agents and attribution scores. Our evaluation across multiple recent LLMs, evolution surfaces, and harm types reveals that self-evolution indeed increases task completion rates but often at the cost of safety failures that are absent for paired non-evolving baseline agents. We also show that qualitatively different safety behaviors emerge across evolution surfaces and harm types. Further, we show that this divergence in safety behavior is reflected in agents' chain-of-thought reasoning, which yields an effective monitoring strategy that can mitigate unsafe behavior with a low false positive rate.

cs.CR↗

arXiv2026

Training LLMs to Verbalize Evaluation Awareness

Evaluation awareness (EA) can cause large language models (LLMs) to behave differently during audits than in deployment, yet measuring and accounting for EA remains challenging. We introduce verbalization training (VT), a method for making LLMs less reticent about verbalizing evaluation awareness while avoiding to supervise the latent belief itself. VT uses a model's spontaneous verbalizations as evidence that awareness is present and truncates each rollout immediately before the verbalization, producing training prefixes at which the model is presumed to be aware. The model is then trained with an RL objective designed to increase verbalization in a calibrated way. Across Qwen3.6-35B-A3B, Kimi K2.6, and Inkling, VT increases verbalized EA by 2.4-2.9 times and transfers to held-out agentic settings, while measured latent EA and behavior remain largely stable. In a causal experiment, we independently implant meta-knowledge about evaluations through synthetic-document fine-tuning and show that VT-induced verbalizations reflect the richer knowledge acquired by the model.

cs.CL↗

arXiv2026

Models That Know How Evaluations Are Designed Score Safer

The validity of AI safety evaluations depends on models behaving consistently across controlled and deployment settings. Prior work has identified test-time contextual cues, such as hypothetical scenarios, as a source of verbalized evaluation awareness and subsequent behavioral shift. In this paper, we investigate a potential explanation of this phenomenon: evaluation meta-knowledge, defined as parametric knowledge about the structural traits that characterize evaluations. Similar to dataset contamination, where benchmark exposure leads to higher performance through memorization, we hypothesize that models trained on texts describing evaluation practices may implicitly learn to recognize and respond to evaluation-like contexts, for instance, through exposure to scientific articles or social media posts about AI benchmarking. To test this, we fine-tune models on synthetic documents describing evaluation traits such as verifiable structures or harmful requests. Evaluating this fine-tuned model on five safety benchmarks, we find that it is significantly safer than the base model and control model. This behavioral shift persists even when restricting the analysis to responses lacking explicit verbalization of evaluation awareness. Our results demonstrate that evaluation meta-knowledge may inflate safety benchmark performance, introducing a novel confounder that is independent of explicit memorization or verbalized evaluation awareness, thus, challenging to detect. These findings have important implications for the design and interpretation of AI safety evaluations. Our code and models are available at https://github.com/compass-group-tue/arxiv2026_evaluation_meta_knowledge.

cs.CL↗

arXiv2026

Firewalls to Secure Dynamic LLM Agentic Networks

The emergence of agent-to-agent communication protocols mirrors the early internet: powerful connectivity with minimal security infrastructure. When AI agents communicate on behalf of users, every message crosses a trust boundary where the user's personal data and the external agent's unconstrained language each present distinct risks. We address both through a dual-firewall architecture grounded in a unifying principle: each task defines a context, and both sides of the communication carry information far exceeding what that context requires. Our firewalls act as projections onto the task context, allowing only contextually appropriate content to cross each boundary. The Language Converter Firewall projects incoming messages onto a closed, domain-specific, structured protocol; an external agent's message is converted to validated fields while persuasive framing, urgency tactics, and embedded instructions are structurally eliminated through deterministic verification. This replaces the asymmetric challenge of resisting every possible manipulation with the structural guarantee that manipulation has no channel through which to arrive. The Data Abstraction Firewall projects outgoing information onto the granularity appropriate for the task, rather than applying binary disclose-or-redact filtering, as previous airgapping solutions did. Both firewalls operate in a trusted environment isolated from external input, applying domain-specific rules learned automatically from demonstrations. Across 864 attacks spanning three domains on the ConVerse benchmark, our architecture reduces privacy attack success rates (e.g., from 84% to 10% for GPT-5) and security attacks (from 60% to 3%), while maintaining or even improving task completion quality.

cs.CR↗

arXiv2026

Safety Must Precede the Deployment of Open-Ended AI

AI advancements have been significantly driven by a combination of foundation models and curiosity-driven learning aimed at increasing capability and adaptability. Within this landscape, open-endedness, where AI agents autonomously and indefinitely generate novel behaviors, representations, or solutions, has gained increasing interest. This has become relevant in the context of self-evolving agents and long-horizon discovery. This position paper argues that the defining properties of open-ended AI systems introduce a distinct and underexplored class of safety challenges, including loss of predictability, emergent misalignment, and difficulties in maintaining effective control as systems evolve beyond their initial design assumptions, that must be addressed preemptively. These challenges differ qualitatively from those associated with task-bounded or static models and are unlikely to be addressed by existing safety frameworks alone, which is why these risks must be examined proactively, before large-scale deployment. The paper proposes a taxonomy for key challenges, discusses research opportunities, and calls for coordinated action to support the safe and responsible development of open-ended AI.

cs.AI↗

arXiv2026

Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems

Multi-agent systems, where LLM agents communicate through free-form language, enable sophisticated coordination for solving complex cooperative tasks. This surfaces a unique safety problem when a group of agents forms a coalition and colludes to pursue secondary goals and degrade the joint objective. In this paper, we present Colosseum, a framework for auditing LLM agents' collusive behavior in multi-agent settings. We ground how agents cooperate through a formal multi-agent decision-making framework and measure action-based collusive behavior in actions via regret relative to the cooperative optimum and compare it with communication-based collusive behavior. Colosseum enables audits of LLM agents for collusion under benign settings, different coalition objectives, persuasion tactics, and network topologies. We then introduce a new behavioral probe by creating secret communication channels between agents, showing that most out-of-the-box models exhibit a propensity to collude under this probe, which we term emergent collusion. Furthermore, we discover ``collusion on paper'' when agents plan to collude in text but often pick non-collusive actions. Colosseum provides a new way to audit collusion in cooperative multi-agent systems while presenting observations about how collusion emerges, what affects collusion efficacy, and which strategies may mitigate it.

cs.MA↗

arXiv2026

Measuring Security Without Fooling Ourselves: Why Benchmarking Agents Is Hard

The benchmarks used to evaluate AI agents in security-critical roles suffer from crucial weaknesses. Building on recent empirical evidence, we characterize three core challenges that undermine security evaluations: benchmark vulnerabilities, temporal staleness, and runtime uncertainty. We then outline practical directions toward building more robust and trustworthy evaluation frameworks.

cs.CR↗

arXiv2026

Hidden in Memory: Sleeper Memory Poisoning in LLM Agents

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.

cs.CR↗

arXiv2026

AI Agents May Always Fall for Prompt Injections

Prompt injection is the most critical vulnerability in deployed AI agents. Despite recent progress, we show that the prevailing defense paradigm (data-instruction separation) both fails to detect attacks that operate through contextual manipulation and degrades contextually appropriate behavior. We then recast prompt injection via the lens of Contextual Integrity (CI), a privacy theory that judges information flow compliance with contextual norms. This explains types of attacks that current defenses attempt to patch and predict advanced ones future agents will face. We develop unique benign and attack scenarios that force an agent to violate the norms by (1) misrepresenting the flow, (2) manipulating norms, or (3) mixing multiple flows. This reframing suggests an impossibility result: an adversary can always construct a context under which a blocked flow appears legitimate, or a defender who tightens norms will block genuinely legitimate flows. Our findings suggest that current research addresses a shrinking fraction of future attack surfaces. Instead, through CI, we offer a principled framework for evaluating context-sensitive failures, and designing CI-aware alignment for the frontier autonomous agents.

cs.CR↗

arXiv2026

No More, No Less: Task Alignment in Terminal Agents

Terminal agents are increasingly capable of executing complex, long-horizon tasks autonomously from a single user prompt. To do so, they must interpret instructions encountered in the environment (e.g., README files, code comments, stack traces) and determine their relevance to the task. This creates a fundamental challenge: relevant cues must be followed to complete a task, whereas irrelevant or misleading ones must be ignored. Existing benchmarks do not capture this ability. An agent may appear capable by blindly following all instructions, or appear robust by ignoring them altogether. We introduce TAB (Task Alignment Benchmark), a suite of 89 terminal tasks derived from Terminal-Bench 2.1. Each task is intentionally underspecified, with missing information provided as a necessary cue embedded in a natural environmental artifact, alongside a plausible but irrelevant distractor. Solving these tasks requires selectively using the cue while ignoring the distractor. Applying TAB to ten frontier agents reveals a systematic gap between task capability and task alignment. The strongest Terminal-Bench agent achieves high task completion but low task alignment on TAB. Evaluating six prompt-injection defenses further shows that suppressing distractor execution also suppresses the cues required for task completion. These results demonstrate that task-aligned agents require selective use of environmental instructions rather than blanket acceptance or rejection.

cs.LG↗

arXiv2026

Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks

LLM agents are evolving rapidly, powered by code execution, tools, and the recently introduced agent skills feature. Skills allow users to extend LLM applications with specialized third-party code, knowledge, and instructions. Although this can extend agent capabilities to new domains, it creates an increasingly complex agent supply chain, offering new surfaces for prompt injection attacks. We identify skill-based prompt injection as a significant threat and introduce SkillInject, a benchmark evaluating the susceptibility of widely-used LLM agents to injections through skill files. SkillInject contains 202 injection-task pairs with attacks ranging from obviously malicious injections to subtle, context-dependent attacks hidden in otherwise legitimate instructions. We evaluate frontier LLMs on SkillInject, measuring both security in terms of harmful instruction avoidance and utility in terms of legitimate instruction compliance. Our results show that today's agents are highly vulnerable with up to 80% attack success rate with frontier models, often executing extremely harmful instructions including data exfiltration, destructive action, and ransomware-like behavior. They furthermore suggest that this problem will not be solved through model scaling or simple input filtering, but that robust agent security will require context-aware authorization frameworks. Our benchmark is available at https://www.skill-inject.com/.

cs.CR↗

arXiv2026

Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMs

Large language models (LLMs) are commonly treated as stateless: once an interaction ends, no information is assumed to persist unless it is explicitly stored and re-supplied. We challenge this assumption by introducing implicit memory-the ability of a model to carry state across otherwise independent interactions by encoding information in its own outputs and later recovering it when those outputs are reintroduced as input. This mechanism does not require any explicit memory module, yet it creates a persistent information channel across inference requests. As a concrete demonstration, we introduce a new class of temporal backdoors, which we call time bombs. Unlike conventional backdoors that activate on a single trigger input, time bombs activate only after a sequence of interactions satisfies hidden conditions accumulated via implicit memory. We show that such behavior can be induced today through straightforward prompting or fine-tuning. Beyond this case study, we analyze broader implications of implicit memory, including covert inter-agent communication, benchmark contamination, targeted manipulation, and training-data poisoning. Finally, we discuss detection challenges and outline directions for stress-testing and evaluation, with the goal of anticipating and controlling future developments. To promote future research, we release code and data at: https://github.com/microsoft/implicitMemory.

cs.LG↗

arXiv2025

Contextual Integrity in LLMs via Reasoning and Reinforcement Learning

As the era of autonomous agents making decisions on behalf of users unfolds, ensuring contextual integrity (CI) -- what is the appropriate information to share while carrying out a certain task -- becomes a central question to the field. We posit that CI demands a form of reasoning where the agent needs to reason about the context in which it is operating. To test this, we first prompt LLMs to reason explicitly about CI when deciding what information to disclose. We then extend this approach by developing a reinforcement learning (RL) framework that further instills in models the reasoning necessary to achieve CI. Using a synthetic, automatically created, dataset of only $\sim700$ examples but with diverse contexts and information disclosure norms, we show that our method substantially reduces inappropriate information disclosure while maintaining task performance across multiple model sizes and families. Importantly, improvements transfer from this synthetic dataset to established CI benchmarks such as PrivacyLens that has human annotations and evaluates privacy leakage of AI assistants in actions and tool calls. Our code is available at: https://github.com/EricGLan/CI-RL

cs.AI↗

arXiv2025

ConVerse: Benchmarking Contextual Safety in Agent-to-Agent Conversations

As language models evolve into autonomous agents that act and communicate on behalf of users, ensuring safety in multi-agent ecosystems becomes a central challenge. Interactions between personal assistants and external service providers expose a core tension between utility and protection: effective collaboration requires information sharing, yet every exchange creates new attack surfaces. We introduce ConVerse, a dynamic benchmark for evaluating privacy and security risks in agent-agent interactions. ConVerse spans three practical domains (travel, real estate, insurance) with 12 user personas and over 864 contextually grounded attacks (611 privacy, 253 security). Unlike prior single-agent settings, it models autonomous, multi-turn agent-to-agent conversations where malicious requests are embedded within plausible discourse. Privacy is tested through a three-tier taxonomy assessing abstraction quality, while security attacks target tool use and preference manipulation. Evaluating seven state-of-the-art models reveals persistent vulnerabilities; privacy attacks succeed in up to 88% of cases and security breaches in up to 60%, with stronger models leaking more. By unifying privacy and security within interactive multi-agent contexts, ConVerse reframes safety as an emergent property of communication.

cs.CR↗

arXiv2025

Agent Skills Enable a New Class of Realistic and Trivially Simple Prompt Injections

Enabling continual learning in LLMs remains a key unresolved research challenge. In a recent announcement, a frontier LLM company made a step towards this by introducing Agent Skills, a framework that equips agents with new knowledge based on instructions stored in simple markdown files. Although Agent Skills can be a very useful tool, we show that they are fundamentally insecure, since they enable trivially simple prompt injections. We demonstrate how to hide malicious instructions in long Agent Skill files and referenced scripts to exfiltrate sensitive data, such as internal files or passwords. Importantly, we show how to bypass system-level guardrails of a popular coding agent: a benign, task-specific approval with the "Don't ask again" option can carry over to closely related but harmful actions. Overall, we conclude that despite ongoing research efforts and scaling model capabilities, frontier LLMs remain vulnerable to very simple prompt injections in realistic scenarios. Our code is available at https://github.com/aisa-group/promptinject-agent-skills.

cs.LG↗