How Catastrophic is Your LLM? Certifying Risks in Conversation

摘要

Large Language Models (LLMs) can produce catastrophic responses in conversational settings that pose serious risks to public safety and security. Existing evaluations often fail to fully reveal these vulnerabilities because they rely on fixed attack prompt sequences, lack statistical guarantees, and do not scale to the vast space of multi-turn conversations. In this work, we propose C$^3$LLM, a novel, principled Certification framework for Catastrophic risks in multi-turn Conversation for LLMs that bounds the probability of an LLM generating catastrophic responses under multi-turn conversation distributions with statistical guarantees. We model multi-turn conversations as probability distributions over query sequences, represented by a Markov process on a query graph whose edges encode semantic similarity to capture realistic conversational flow, and quantify catastrophic risks using confidence intervals. We define several inexpensive and practical distributions—random node, graph path, and adaptive with rejection. Our results demonstrate that these distributions can reveal substantial catastrophic risks in frontier models, with certified lower bounds as high as 70\% for the worst model, highlighting the urgent need for improved safety training strategies in frontier LLMs.