← Search

Daniil Dzenhaliou

2 accepted papers

2026

Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols

ICLR 2026poster

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 testing with exploits that use the deployment context to subtly complete harmful side tasks, such as backdoor insertion. In pr…

Cited by 0SourceScholar
2025

INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge

ICLR 2025spotlight

The performance differential of large language models (LLM) between languages hinders their effective deployment in many regions, inhibiting the potential economic and societal value of generative AI tools in many communities. However, the development of functional LLMs in many languages (i.e., mult…

Cited by 9SourcePDFScholar