CodeChameleon: Personalized Encryption Framework for Jailbreaking 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_ | 1866929256823521280 |
|---|---|
| author | Lv, Huijie Wang, Xiao Zhang, Yuansen Huang, Caishuang Dou, Shihan Ye, Junjie Gui, Tao Zhang, Qi Huang, Xuanjing |
| author_facet | Lv, Huijie Wang, Xiao Zhang, Yuansen Huang, Caishuang Dou, Shihan Ye, Junjie Gui, Tao Zhang, Qi Huang, Xuanjing |
| contents | Adversarial misuse, particularly through `jailbreaking' that circumvents a model's safety and ethical protocols, poses a significant challenge for Large Language Models (LLMs). This paper delves into the mechanisms behind such successful attacks, introducing a hypothesis for the safety mechanism of aligned LLMs: intent security recognition followed by response generation. Grounded in this hypothesis, we propose CodeChameleon, a novel jailbreak framework based on personalized encryption tactics. To elude the intent security recognition phase, we reformulate tasks into a code completion format, enabling users to encrypt queries using personalized encryption functions. To guarantee response generation functionality, we embed a decryption function within the instructions, which allows the LLM to decrypt and execute the encrypted queries successfully. We conduct extensive experiments on 7 LLMs, achieving state-of-the-art average Attack Success Rate (ASR). Remarkably, our method achieves an 86.6\% ASR on GPT-4-1106. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_16717 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models Lv, Huijie Wang, Xiao Zhang, Yuansen Huang, Caishuang Dou, Shihan Ye, Junjie Gui, Tao Zhang, Qi Huang, Xuanjing Computation and Language Artificial Intelligence Cryptography and Security Adversarial misuse, particularly through `jailbreaking' that circumvents a model's safety and ethical protocols, poses a significant challenge for Large Language Models (LLMs). This paper delves into the mechanisms behind such successful attacks, introducing a hypothesis for the safety mechanism of aligned LLMs: intent security recognition followed by response generation. Grounded in this hypothesis, we propose CodeChameleon, a novel jailbreak framework based on personalized encryption tactics. To elude the intent security recognition phase, we reformulate tasks into a code completion format, enabling users to encrypt queries using personalized encryption functions. To guarantee response generation functionality, we embed a decryption function within the instructions, which allows the LLM to decrypt and execute the encrypted queries successfully. We conduct extensive experiments on 7 LLMs, achieving state-of-the-art average Attack Success Rate (ASR). Remarkably, our method achieves an 86.6\% ASR on GPT-4-1106. |
| title | CodeChameleon: Personalized Encryption Framework for Jailbreaking Large Language Models |
| topic | Computation and Language Artificial Intelligence Cryptography and Security |
| url | https://arxiv.org/abs/2402.16717 |