activity
20242026
collaborators

9 papers

cs.CR2026

Stealing Reasoning Traces from Proprietary LLM APIs

Alexander Panfilov, David Schmotz, Ilia Shumailov +5

Leading large language model providers now conceal their models' step-by-step reasoning, or chain-of-thought, to protect intellectual property and limit information leakage. Rather…

cs.AI2026

CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs

Joachim Schaeffer, Thomas Jiralerspong, Alexander Panfilov +4

AI control protocols oversee untrusted models by monitoring their actions and modifying potentially unsafe steps, often using a trusted model. This partially tampers with the untru…

cs.LG2026

Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs

Alexander Panfilov, Peter Romov, Igor Shilov +3

We show that AI agents are capable of discovering novel algorithms for adversarial attacks against LLMs, advancing the state of the art on white-box jailbreaking and prompt injecti…

cs.LG2026

Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols

Mikhail Terekhov, Alexander Panfilov, Daniil Dzenhaliou +4

AI control protocols serve as a defense mechanism to stop untrusted LLM agents from causing harm in autonomous settings. Prior work treats this as a security problem, stress testin…

cs.LG2026

ASIDE: Architectural Separation of Instructions and Data in Language Models

Egor Zverev, Evgenii Kortukov, Alexander Panfilov +5

Despite their remarkable performance, large language models lack elementary safety features, making them susceptible to numerous malicious attacks. In particular, previous work has…

cs.AI2026

Capability-Based Scaling Trends for LLM-Based Red-Teaming

Alexander Panfilov, Paul Kassianik, Maksym Andriushchenko +1

As large language models grow in capability and agency, identifying vulnerabilities through red-teaming becomes vital for safe deployment. However, traditional prompt-engineering a…