activity
20242026
collaborators

9 papers

cs.AI2026

Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets

Jack Hopkins, Dipika Khullar, Fabien Roger

Black box auditing of language models is an essential pre-deployment tool, but it may miss subtle forms of misalignment and hidden information. To better elicit hidden information…

cs.CR2026

Narrow Secret Loyalty Dodges Black-Box Audits

Alfie Lamerton, Fabien Roger

Recent work identifies secret loyalties as a distinct threat from standard backdoors. A secret loyalty causes a model to covertly advance the interests of a specific principal whil…

cs.CR2026

SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors

Elle Najt, Colin Toft, Tyler Tracy +2

Since autonomous coding agents generate complex behaviors at high-volume, we may want to use other LLMs to monitor actions to reduce the risk from dangerous misaligned behavior. To…

cs.AI2026

Classifier Context Rot: Monitor Performance Degrades with Context Length

Sam Martin, Fabien Roger

Monitoring coding agents for dangerous behavior using language models requires classifying transcripts that often exceed 500K tokens, but prior agent monitoring benchmarks rarely c…

cs.AI2026

How Useful Is Cross-Domain Generalization for Training LLM Monitors?

Sam Martin, Fabien Roger

Using prompted language models as classifiers enables classification in domains with limited training data, but misses some of the robustness and performance benefits that fine-tun…

cs.AI2026

Self-Attribution Bias: When AI Monitors Go Easy on Themselves

Dipika Khullar, Jack Hopkins, Rowan Wang +1

Agentic systems increasingly rely on language models to monitor their own behavior. For example, coding agents may self critique generated code for pull request approval or assess…