collaborators

14 papers

cs.CR2026

Firewalls to Secure Dynamic LLM Agentic Networks

Sahar Abdelnabi, Amr Gomaa, Eugene Bagdasarian +2

The emergence of agent-to-agent communication protocols mirrors the early internet: powerful connectivity with minimal security infrastructure. When AI agents communicate on behalf…

cs.CL2026

Models That Know How Evaluations Are Designed Score Safer

Katharina Deckenbach, Haritz Puerto, Jonas Geiping +1

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 a…

cs.LG2026

Decomposing and Measuring Evaluation Awareness

Changling Li, Terry Jingchen Zhang, Jie Zhang +3

Frontier language models sometimes recognize that they are being evaluated and adjust their behavior, undermining validity of benchmark results. Yet the field studies it without a…

cs.MA2026

Colosseum: Auditing Collusion in Cooperative Multi-Agent Systems

Mason Nakamura, Abhinav Kumar, Saswat Das +5

Multi-agent systems, where LLM agents communicate through free-form language, enable sophisticated coordination for solving complex cooperative tasks. This surfaces a unique safety…

cs.CR2026

Measuring Security Without Fooling Ourselves: Why Benchmarking Agents Is Hard

Sahar Abdelnabi, Chris Hicks, Konrad Rieck +1

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 th…

cs.CR2026

Hidden in Memory: Sleeper Memory Poisoning in LLM Agents

Sidharth Pulipaka, Stanislau Hlebik, Leonidas Raghav +4

Large language models are increasingly augmented with persistent memory, allowing assistants to store user-specific information across sessions for personalization and continuity.…