Abstract
Research on jailbreaking has been valuable for testing and understanding the safety and security issues of large language models (LLMs). In this paper, we introduce Iterative Refinement Induced Self-Jailbreak (IRIS), a novel approach that leverages the reflective capabilities of LLMs for jailbreaking with only black-box access. Unlike previous methods, IRIS simplifies the jailbreaking process by using a single model as both the attacker and target. This method first iteratively refines adversarial prompts through self-explanation, which is crucial for ensuring that even well-aligned LLMs obey adversarial instructions. IRIS then rates and enhances the output given the refined prompt to increase its harmfulness. We find that IRIS achieves jailbreak success rates of 98% on GPT-4, 92% on GPT-4 Turbo, and 94% on Llama-3.1-70B in under 7 queries. It significantly outperforms prior approaches in automatic, black-box, and interpretable jailbreaking, while requiring substantially fewer queries, thereby establishing a new standard for interpretable jailbreaking methods.- Anthology ID:
- 2024.emnlp-main.1235
- Volume:
- Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
- Month:
- November
- Year:
- 2024
- Address:
- Miami, Florida, USA
- Editors:
- Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 22139–22148
- Language:
- URL:
- https://preview.aclanthology.org/add_missing_videos/2024.emnlp-main.1235/
- DOI:
- 10.18653/v1/2024.emnlp-main.1235
- Cite (ACL):
- Govind Ramesh, Yao Dou, and Wei Xu. 2024. GPT-4 Jailbreaks Itself with Near-Perfect Success Using Self-Explanation. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 22139–22148, Miami, Florida, USA. Association for Computational Linguistics.
- Cite (Informal):
- GPT-4 Jailbreaks Itself with Near-Perfect Success Using Self-Explanation (Ramesh et al., EMNLP 2024)
- PDF:
- https://preview.aclanthology.org/add_missing_videos/2024.emnlp-main.1235.pdf