paper-with-me

홈 › Papers

Geneshift: Impact of different scenario shift on Jailbreaking LLM

2025-04-10 · Tianyi Wu, Zhiwei Xue, Yue Liu, Jiaheng Zhang, Bryan Hooi, See-Kiong Ng

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 evaluation, existing jailbreak attack methods fail to output detailed contents to satisfy the harmful request, leading to poor performance on GPT-based evaluation. To this end, we propose a black-box jailbreak attack termed GeneShift, by using a genetic algorithm to optimize the scenario shifts. Firstly, we observe that the malicious queries perform optimally under different scenario shifts. Based on it, we develop a genetic algorithm to evolve and select the hybrid of scenario shifts. It guides our method to elicit detailed and actionable harmful responses while keeping the seemingly benign facade, improving stealthiness. Extensive experiments demonstrate the superiority of GeneShift. Notably, GeneShift increases the jailbreak success rate from 0% to 60% when direct prompting alone would fail.

📄 PDF Abstract BibTeX arXiv:2504.08104

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models

2024-12-22 · Lang Gao, Jiahui Geng, Xiangliang Zhang, Preslav Nakov 외

Jailbreaking in Large Language Models (LLMs) is a major security concern as it can deceive LLMs to generate harmful text. Yet, there is still insufficient understanding of how jailbreaking works, which makes it hard to d…

Bayesian Optimization

Robustifying Safety-Aligned Large Language Models through Clean Data Curation

2024-05-24 · Xiaoqun Liu, Jiacheng Liang, Muchao Ye, Zhaohan Xi

Large language models (LLMs) are vulnerable when trained on datasets containing harmful content, which leads to potential jailbreaking attacks in two scenarios: the integration of harmful texts within crowdsourced data u…

Safety Alignment

Benchmarking LLM Guardrails in Handling Multilingual Toxicity

2024-10-29 · Yahan Yang, Soham Dan, Dan Roth, Insup Lee

With the ubiquity of Large Language Models (LLMs), guardrails have become crucial to detect and defend against toxic content. However, with the increasing pervasiveness of LLMs in multilingual scenarios, their effectiven…

Benchmarking

Pruning for Protection: Increasing Jailbreak Resistance in Aligned LLMs Without Fine-Tuning

2024-01-19 · Adib Hasan, Ileana Rugina, Alex Wang

This paper investigates the impact of model compression on the way Large Language Models (LLMs) process prompts, particularly concerning jailbreak resistance. We show that moderate WANDA pruning can enhance resistance to…

Model Compression

How to Trick Your AI TA: A Systematic Study of Academic Jailbreaking in LLM Code Evaluation

2025-12-11 · Devanshu Sahoo, Vasudev Majhi, Arjun Neekhra, Yash Sinha 외 arxiv

The use of Large Language Models (LLMs) as automatic judges for code evaluation is becoming increasingly prevalent in academic environments. But their reliability can be compromised by students who may employ adversarial…