4 papers
Stateless Yet Not Forgetful: Implicit Memory as a Hidden Channel in LLMs
Ahmed Salem, Andrew Paverd, Sahar Abdelnabi
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 ch…
ConVerse: Benchmarking Contextual Safety in Agent-to-Agent Conversations
Amr Gomaa, Ahmed Salem, Sahar Abdelnabi
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 be…
The Hawthorne Effect in Reasoning Models: Evaluating and Steering Test Awareness
Sahar Abdelnabi, Ahmed Salem
Reasoning-focused LLMs sometimes alter their behavior when they detect that they are being evaluated, which can lead them to optimize for test-passing performance or to comply more…
LLMail-Inject: A Dataset from a Realistic Adaptive Prompt Injection Challenge
Sahar Abdelnabi, Aideen Fay, Ahmed Salem +22
Indirect Prompt Injection attacks exploit the inherent limitation of Large Language Models (LLMs) to distinguish between instructions and data in their inputs. Despite numerous def…