collaborators

5 papers

cs.LG2025

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.LG2025

Strategic Dishonesty Can Undermine AI Safety Evaluations of Frontier LLMs

Alexander Panfilov, Evgenii Kortukov, Kristina Nikolić +6

Large language model (LLM) developers aim for their models to be honest, helpful, and harmless. However, when faced with malicious requests, models are trained to refuse, sacrifici…

cs.AI2025

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…

cs.LG2025

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.LG2024

An Interpretable N-gram Perplexity Threat Model for Large Language Model Jailbreaks

Valentyn Boreiko, Alexander Panfilov, Vaclav Voracek +2

A plethora of jailbreaking attacks have been proposed to obtain harmful responses from safety-tuned LLMs. These methods largely succeed in coercing the target output in their origi…