paper-with-me

Papers

LLM Jailbreak Oracle

2025-06-17 · Shuyi Lin, Anshuman Suri, Alina Oprea, Cheng Tan

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.

📄 PDF Abstract BibTeX arXiv:2506.17299

Code (0)

등록된 구현이 없습니다.

Tasks

LLM Jailbreak

Similar Papers 제목 키워드 기반

Fuzz-Testing Meets LLM-Based Agents: An Automated and Efficient Framework for Jailbreaking Text-To-Image Generation Models

2024-08-01 · Yingkai Dong, Xiangtao Meng, Ning Yu, Zheng Li 외

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+2

TEMPLATEFUZZ: Fine-Grained Chat Template Fuzzing for Jailbreaking and Red Teaming LLMs

2026-04-14 · Qingchao Shen, Zibo Xiao, Lili Huang, Enwei Hu 외 arxiv

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 Teaming

Randomized Smoothing Meets Vision-Language Models

2025-09-19 · Emmanouil Seferis, Changshun Wu, Stefanos Kollias, Saddek Bensalem 외 arxiv

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

2025-09-28 · Shuyi Lin, Tian Lu, Zikai Wang, Bo Wen 외 arxiv

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

2024-05-30 · Zhenxing Niu, Yuyao Sun, Haoxuan Ji, Zheng Lin 외

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