Improved Techniques for Optimization-Based Jailbreaking on Large Language Models
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_ | 1866914825195487232 |
|---|---|
| author | Jia, Xiaojun Pang, Tianyu Du, Chao Huang, Yihao Gu, Jindong Liu, Yang Cao, Xiaochun Lin, Min |
| author_facet | Jia, Xiaojun Pang, Tianyu Du, Chao Huang, Yihao Gu, Jindong Liu, Yang Cao, Xiaochun Lin, Min |
| contents | Large language models (LLMs) are being rapidly developed, and a key component of their widespread deployment is their safety-related alignment. Many red-teaming efforts aim to jailbreak LLMs, where among these efforts, the Greedy Coordinate Gradient (GCG) attack's success has led to a growing interest in the study of optimization-based jailbreaking techniques. Although GCG is a significant milestone, its attacking efficiency remains unsatisfactory. In this paper, we present several improved (empirical) techniques for optimization-based jailbreaks like GCG. We first observe that the single target template of "Sure" largely limits the attacking performance of GCG; given this, we propose to apply diverse target templates containing harmful self-suggestion and/or guidance to mislead LLMs. Besides, from the optimization aspects, we propose an automatic multi-coordinate updating strategy in GCG (i.e., adaptively deciding how many tokens to replace in each step) to accelerate convergence, as well as tricks like easy-to-hard initialisation. Then, we combine these improved technologies to develop an efficient jailbreak method, dubbed I-GCG. In our experiments, we evaluate on a series of benchmarks (such as NeurIPS 2023 Red Teaming Track). The results demonstrate that our improved techniques can help GCG outperform state-of-the-art jailbreaking attacks and achieve nearly 100% attack success rate. The code is released at https://github.com/jiaxiaojunQAQ/I-GCG. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_21018 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Improved Techniques for Optimization-Based Jailbreaking on Large Language Models Jia, Xiaojun Pang, Tianyu Du, Chao Huang, Yihao Gu, Jindong Liu, Yang Cao, Xiaochun Lin, Min Machine Learning Computation and Language Cryptography and Security Large language models (LLMs) are being rapidly developed, and a key component of their widespread deployment is their safety-related alignment. Many red-teaming efforts aim to jailbreak LLMs, where among these efforts, the Greedy Coordinate Gradient (GCG) attack's success has led to a growing interest in the study of optimization-based jailbreaking techniques. Although GCG is a significant milestone, its attacking efficiency remains unsatisfactory. In this paper, we present several improved (empirical) techniques for optimization-based jailbreaks like GCG. We first observe that the single target template of "Sure" largely limits the attacking performance of GCG; given this, we propose to apply diverse target templates containing harmful self-suggestion and/or guidance to mislead LLMs. Besides, from the optimization aspects, we propose an automatic multi-coordinate updating strategy in GCG (i.e., adaptively deciding how many tokens to replace in each step) to accelerate convergence, as well as tricks like easy-to-hard initialisation. Then, we combine these improved technologies to develop an efficient jailbreak method, dubbed I-GCG. In our experiments, we evaluate on a series of benchmarks (such as NeurIPS 2023 Red Teaming Track). The results demonstrate that our improved techniques can help GCG outperform state-of-the-art jailbreaking attacks and achieve nearly 100% attack success rate. The code is released at https://github.com/jiaxiaojunQAQ/I-GCG. |
| title | Improved Techniques for Optimization-Based Jailbreaking on Large Language Models |
| topic | Machine Learning Computation and Language Cryptography and Security |
| url | https://arxiv.org/abs/2405.21018 |