paper-with-me

Papers

Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMs

2024-02-21 · Xiaoxia Li, Siyuan Liang, Jiyi Zhang, Han Fang, Aishan Liu, Ee-Chien Chang

Large Language Models (LLMs), used in creative writing, code generation, and translation, generate text based on input sequences but are vulnerable to jailbreak attacks, where crafted prompts induce harmful outputs. Most jailbreak prompt methods use a combination of jailbreak templates followed by questions to ask to create jailbreak prompts. However, existing jailbreak prompt designs generally suffer from excessive semantic differences, resulting in an inability to resist defenses that use simple semantic metrics as thresholds. Jailbreak prompts are semantically more varied than the original questions used for queries. In this paper, we introduce a Semantic Mirror Jailbreak (SMJ) approach that bypasses LLMs by generating jailbreak prompts that are semantically similar to the original question. We model the search for jailbreak prompts that satisfy both semantic similarity and jailbreak validity as a multi-objective optimization problem and employ a standardized set of genetic algorithms for generating eligible prompts. Compared to the baseline AutoDAN-GA, SMJ achieves attack success rates (ASR) that are at most 35.4% higher without ONION defense and 85.2% higher with ONION defense. SMJ's better performance in all three semantic meaningfulness metrics of Jailbreak Prompt, Similarity, and Outlier, also means that SMJ is resistant to defenses that use those metrics as thresholds.

📄 PDF Abstract BibTeX arXiv:2402.14872

Code (0)

등록된 구현이 없습니다.

Tasks

Code GenerationSemantic SimilaritySemantic Textual Similarity

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

MirrorShield: Towards Universal Defense Against Jailbreaks via Entropy-Guided Mirror Crafting

2025-03-17 · Rui Pu, Chaozhuo Li, Rui Ha, Litian Zhang 외

Defending large language models (LLMs) against jailbreak attacks is crucial for ensuring their safe deployment. Existing defense strategies typically rely on predefined static criteria to differentiate between harmful an…

AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

2023-10-03 · Xiaogeng Liu, Nan Xu, Muhao Chen, Chaowei Xiao

The aligned Large Language Models (LLMs) are powerful language understanding and decision-making tools that are created through extensive alignment with human feedback. However, these large models remain susceptible to j…

Decision Making

Geneshift: Impact of different scenario shift on Jailbreaking LLM

2025-04-10 · Tianyi Wu, Zhiwei Xue, Yue Liu, Jiaheng Zhang 외

Jailbreak attacks, which aim to cause LLMs to perform unrestricted behaviors, have become a critical and challenging direction in AI safety. Despite achieving the promising attack success rate using dictionary-based eval…

Stealthy Jailbreak Attacks on Large Language Models via Benign Data Mirroring

2024-10-28 · Honglin Mu, Han He, Yuxin Zhou, Yunlong Feng 외

Large language model (LLM) safety is a critical issue, with numerous studies employing red team testing to enhance model security. Among these, jailbreak methods explore potential vulnerabilities by crafting malicious pr…

Language ModelingLanguage ModellingLarge Language Model

xJailbreak: Representation Space Guided Reinforcement Learning for Interpretable LLM Jailbreaking

2025-01-28 · Sunbowen Lee, Shiwen Ni, Chi Wei, Shuaimin Li 외

Safety alignment mechanism are essential for preventing large language models (LLMs) from generating harmful information or unethical content. However, cleverly crafted prompts can bypass these safety measures without ac…

Reinforcement Learning (RL)Safety Alignment