تقرير
SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner
| العنوان: | SelfDefend: LLMs Can Defend Themselves against Jailbreaking in a Practical Manner |
|---|---|
| المؤلفون: | Wang, Xunguang, Wu, Daoyuan, Ji, Zhenlan, Li, Zongjie, Ma, Pingchuan, Wang, Shuai, Li, Yingjiu, Liu, Yang, Liu, Ning, Rahmel, Juergen |
| سنة النشر: | 2024 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Cryptography and Security, Computer Science - Artificial Intelligence |
| الوصف: | Jailbreaking is an emerging adversarial attack that bypasses the safety alignment deployed in off-the-shelf large language models (LLMs) and has evolved into four major categories: optimization-based attacks such as Greedy Coordinate Gradient (GCG), jailbreak template-based attacks such as "Do-Anything-Now", advanced indirect attacks like DrAttack, 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 delay 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 defense instance to concurrently protect the target LLM instance in the normal stack and collaborate with it for checkpoint-based access control. The effectiveness of SelfDefend builds upon our observation that existing LLMs (both target and defense LLMs) have the capability to identify harmful prompts or intentions in user queries, which we empirically validate using the commonly used GPT-3.5/4 models across all major jailbreak attacks. Our measurements show that SelfDefend enables GPT-3.5 to suppress the attack success rate (ASR) by 8.97-95.74% (average: 60%) and GPT-4 by even 36.36-100% (average: 83%), while incurring negligible effects on normal queries. To further improve the defense's robustness and minimize costs, we employ a data distillation approach to tune dedicated open-source defense models. These models outperform four SOTA defenses and match the performance of GPT-4-based SelfDefend, with significantly lower extra delays. We also empirically show that the tuned models are robust to targeted GCG and prompt injection attacks. Comment: This paper completes its earlier vision paper, available at arXiv:2402.15727 |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2406.05498 |
| رقم الأكسشن: | edsarx.2406.05498 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |