paper-with-me

Papers

PAPILLON: Efficient and Stealthy Fuzz Testing-Powered Jailbreaks for LLMs

2024-09-23 · Xueluan Gong, Mingzhe Li, Yilin Zhang, Fengyuan Ran, Chen Chen, Yanjiao Chen, Qian Wang, Kwok-Yan Lam

Large Language Models (LLMs) have excelled in various tasks but are still vulnerable to jailbreaking attacks, where attackers create jailbreak prompts to mislead the model to produce harmful or offensive content. Current jailbreak methods either rely heavily on manually crafted templates, which pose challenges in scalability and adaptability, or struggle to generate semantically coherent prompts, making them easy to detect. Additionally, most existing approaches involve lengthy prompts, leading to higher query costs. In this paper, to remedy these challenges, we introduce a novel jailbreaking attack framework called PAPILLON, which is an automated, black-box jailbreaking attack framework that adapts the black-box fuzz testing approach with a series of customized designs. Instead of relying on manually crafted templates,PAPILLON starts with an empty seed pool, removing the need to search for any related jailbreaking templates. We also develop three novel question-dependent mutation strategies using an LLM helper to generate prompts that maintain semantic coherence while significantly reducing their length. Additionally, we implement a two-level judge module to accurately detect genuine successful jailbreaks. We evaluated PAPILLON on 7 representative LLMs and compared it with 5 state-of-the-art jailbreaking attack strategies. For proprietary LLM APIs, such as GPT-3.5 turbo, GPT-4, and Gemini-Pro, PAPILLONs achieves attack success rates of over 90%, 80%, and 74%, respectively, exceeding existing baselines by more than 60\%. Additionally, PAPILLON can maintain high semantic coherence while significantly reducing the length of jailbreak prompts. When targeting GPT-4, PAPILLON can achieve over 78% attack success rate even with 100 tokens. Moreover, PAPILLON demonstrates transferability and is robust to state-of-the-art defenses. Code: https://github.com/aaFrostnova/Papillon

📄 PDF Abstract BibTeX arXiv:2409.14866

Code (1)

aaFrostnova/Papillon 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
15 Ways to Contact How can i speak to someone at Delta Airlines 설명 없음
Attention 설명 없음
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
{Dispute@FaQ-s}How to file a dispute with Expedia? How to file a dispute with Expedia? To file a complaint against Expedia, first try contacting their customer service directly. You can reach them by phone at…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Weight Decay 설명 없음
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

PAPILLON: Privacy Preservation from Internet-based and Local Language Model Ensembles

2024-10-22 · Li Siyan, Vethavikashini Chithrra Raghuram, Omar Khattab, Julia Hirschberg 외

Users can divulge sensitive information to proprietary LLM providers, raising significant privacy concerns. While open-source models, hosted locally on the user's machine, alleviate some concerns, models that users can h…

Language ModelingLanguage Modelling

JBFuzz: Jailbreaking LLMs Efficiently and Effectively Using Fuzzing

2025-03-12 · Vasudev Gohil

Large language models (LLMs) have shown great promise as language understanding and decision making tools, and they have permeated various aspects of our everyday life. However, their widespread availability also comes w…

Red TeamingSafety Alignment

OBsmith: LLM-Powered JavaScript Obfuscator Testing

2025-10-11 · Shan Jiang, Chenguang Zhu, Sarfraz Khurshid arxiv

JavaScript obfuscators are widely deployed to protect intellectual property and resist reverse engineering, yet their correctness has been largely overlooked compared to performance and resilience. Existing evaluations t…

ShallowJail: Steering Jailbreaks against Large Language Models

2026-02-06 · Shang Liu, Hanyu Pei, Zeyan Liu arxiv

Large Language Models(LLMs) have been successful in numerous fields. Alignment has usually been applied to prevent them from harmful purposes. However, aligned LLMs remain vulnerable to jailbreak attacks that deliberatel…

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models

2025-02-02 · Isha Gupta, David Khachaturov, Robert Mullins

The rise of multimodal large language models has introduced innovative human-machine interaction paradigms but also significant challenges in machine learning safety. Audio-Language Models (ALMs) are especially relevant …