LLM Jailbreak Oracle
As large language models (LLMs) become increasingly deployed in safety-critical applications, the lack of systematic methods to assess their vulnerability to jailbreak attacks presents a critical security gap. We introduce the jailbreak oracle problem: given a model, prompt, and decoding strategy, determine whether a jailbreak response can be generated with likelihood exceeding a specified threshold. This formalization enables a principled study of jailbreak vulnerabilities. Answering the jailbreak oracle problem poses significant computational challenges -- the search space grows exponentially with the length of the response tokens. We present Boa, the first efficient algorithm for solving the jailbreak oracle problem. Boa employs a three-phase search strategy: (1) constructing block lists to identify refusal patterns, (2) breadth-first sampling to identify easily accessible jailbreaks, and (3) depth-first priority search guided by fine-grained safety scores to systematically explore promising low-probability paths. Boa enables rigorous security assessments including systematic defense evaluation, standardized comparison of red team attacks, and model certification under extreme adversarial conditions.
Code (0)
등록된 구현이 없습니다.
Tasks
LLM JailbreakSimilar Papers 제목 키워드 기반
Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation Models
Text-to-image (T2I) generative models have revolutionized content creation by transforming textual descriptions into high-quality images. However, these models are vulnerable to jailbreaking attacks, where carefully craf…
Image GenerationIn-Context LearningLanguage ModellingLarge Language Model+2TEMPLATEFUZZ: Fine-Grained Chat Template Fuzzing for Jailbreaking and Red Teaming LLMs
Large Language Models (LLMs) are increasingly deployed across diverse domains, yet their vulnerability to jailbreak attacks, where adversarial inputs bypass safety mechanisms to elicit harmful outputs, poses significant …
Prompt EngineeringActive LearningRed TeamingRandomized Smoothing Meets Vision-Language Models
Randomized smoothing (RS) is one of the prominent techniques to ensure the correctness of machine learning models, where point-wise robustness certificates can be derived analytically. While RS is well understood for cla…
Quant Fever, Reasoning Blackholes, Schrodinger's Compliance, and More: Probing GPT-OSS-20B
OpenAI's GPT-OSS family provides open-weight language models with explicit chain-of-thought (CoT) reasoning and a Harmony prompt format. We summarize an extensive security evaluation of GPT-OSS-20B that probes the model'…
Efficient Indirect LLM Jailbreak via Multimodal-LLM Jailbreak
This paper focuses on jailbreaking attacks against large language models (LLMs), eliciting them to generate objectionable content in response to harmful user queries. Unlike previous LLM-jailbreak methods that directly o…
Language ModelingLanguage ModellingLarge Language ModelLLM Jailbreak+1