SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917912913117184 |
|---|---|
| author | Wang, Xunguang Wu, Daoyuan Ji, Zhenlan Li, Zongjie Ma, Pingchuan Wang, Shuai Li, Yingjiu Liu, Yang Liu, Ning Rahmel, Juergen |
| author_facet | Wang, Xunguang Wu, Daoyuan Ji, Zhenlan Li, Zongjie Ma, Pingchuan Wang, Shuai Li, Yingjiu Liu, Yang Liu, Ning Rahmel, Juergen |
| contents | Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs) and has evolved into multiple categories: human-based, optimization-based, generation-based, and the recent indirect and multilingual jailbreaks. However, delivering a practical jailbreak defense is challenging because it needs to not only handle all the above jailbreak attacks but also incur negligible delays to user prompts, as well as be compatible with both open-source and closed-source LLMs. Inspired by how the traditional security concept of shadow stacks defends against memory overflow attacks, this paper introduces a generic LLM jailbreak defense framework called SelfDefend, which establishes a shadow LLM as a defense instance (in detection state) to concurrently protect the target LLM instance (in normal answering state) in the normal stack and collaborate with it for checkpoint-based access control. The effectiveness of SelfDefend builds upon our observation that existing LLMs can identify harmful prompts or intentions in user queries, which we empirically validate using mainstream GPT-3.5/4 models against major jailbreak attacks. To further improve the defense's robustness and minimize costs, we employ a data distillation approach to tune dedicated open-source defense models. When deployed to protect GPT-3.5/4, Claude, Llama-2-7b/13b, and Mistral, these models outperform seven state-of-the-art defenses and match the performance of GPT-4-based SelfDefend, with significantly lower extra delays. Further experiments show that the tuned models are robust to adaptive jailbreaks and prompt injections. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_05498 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner Wang, Xunguang Wu, Daoyuan Ji, Zhenlan Li, Zongjie Ma, Pingchuan Wang, Shuai Li, Yingjiu Liu, Yang Liu, Ning Rahmel, Juergen Cryptography and Security Artificial Intelligence Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs) and has evolved into multiple categories: human-based, optimization-based, generation-based, and the recent indirect and multilingual jailbreaks. However, delivering a practical jailbreak defense is challenging because it needs to not only handle all the above jailbreak attacks but also incur negligible delays to user prompts, as well as be compatible with both open-source and closed-source LLMs. Inspired by how the traditional security concept of shadow stacks defends against memory overflow attacks, this paper introduces a generic LLM jailbreak defense framework called SelfDefend, which establishes a shadow LLM as a defense instance (in detection state) to concurrently protect the target LLM instance (in normal answering state) in the normal stack and collaborate with it for checkpoint-based access control. The effectiveness of SelfDefend builds upon our observation that existing LLMs can identify harmful prompts or intentions in user queries, which we empirically validate using mainstream GPT-3.5/4 models against major jailbreak attacks. To further improve the defense's robustness and minimize costs, we employ a data distillation approach to tune dedicated open-source defense models. When deployed to protect GPT-3.5/4, Claude, Llama-2-7b/13b, and Mistral, these models outperform seven state-of-the-art defenses and match the performance of GPT-4-based SelfDefend, with significantly lower extra delays. Further experiments show that the tuned models are robust to adaptive jailbreaks and prompt injections. |
| title | SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2406.05498 |