4 papers · 1 filter
Prompted to Discriminate: Generalizing Malicious-Input Probes in the Wild
Elad David, Max Fomin
LLM agents increasingly rely on activation probes as runtime monitors for prompt injection, jailbreaks, and unsafe requests, reading the model's own hidden state to catch a harmful…
Context Is King: How In-Context Specification Shapes the Geometry of Concepts
Elad David, Max Fomin
Large language models place structured concepts on geometrically faithful manifolds: weekdays lie on a circle, months on another, usually taken to be a fixed world-model the networ…
Internal-State Probes Read the Situation, Not the Action: Three Negative Results for Pre-Action Misalignment Monitoring
Max Fomin, Elad David, Amit LeVi
Probes on model internals could help monitor agentic systems if they identify harmful text or tool actions before those actions are generated. We ask when an internal readout suppo…
When Benchmarks Lie: Evaluating Malicious Prompt Classifiers Under True Distribution Shift
Max Fomin
Detecting prompt injection, jailbreak attacks, and harmful requests is critical for deploying LLM-based agents safely, yet current evaluation practices in this literature overestim…