Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization

Zhexin Zhang, Junxiao Yang, Pei Ke, Fei Mi, Hongning Wang, Minlie Huang


Abstract
While significant attention has been dedicated to exploiting weaknesses in LLMs through jailbreaking attacks, there remains a paucity of effort in defending against these attacks. We point out a pivotal factor contributing to the success of jailbreaks: the intrinsic conflict between the goals of being helpful and ensuring safety. Accordingly, we propose to integrate goal prioritization at both training and inference stages to counteract. Implementing goal prioritization during inference substantially diminishes the Attack Success Rate (ASR) of jailbreaking from 66.4% to 3.6% for ChatGPT. And integrating goal prioritization into model training reduces the ASR from 71.0% to 6.6% for Llama2-13B. Remarkably, even in scenarios where no jailbreaking samples are included during training, our approach slashes the ASR by half. Additionally, our findings reveal that while stronger LLMs face greater safety risks, they also possess a greater capacity to be steered towards defending against such attacks, both because of their stronger ability in instruction following. Our work thus contributes to the comprehension of jailbreaking attacks and defenses, and sheds light on the relationship between LLMs’ capability and safety. Our code is available at https://github.com/thu-coai/JailbreakDefense_GoalPriority.
Anthology ID:
2024.acl-long.481
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
8865–8887
Language:
URL:
https://aclanthology.org/2024.acl-long.481
DOI:
10.18653/v1/2024.acl-long.481
Bibkey:
Cite (ACL):
Zhexin Zhang, Junxiao Yang, Pei Ke, Fei Mi, Hongning Wang, and Minlie Huang. 2024. Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 8865–8887, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization (Zhang et al., ACL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.acl-long.481.pdf