Rapid Optimization for Jailbreaking LLMs via Subconscious Exploitation and Echopraxia
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913227509596160 |
|---|---|
| author | Shen, Guangyu Cheng, Siyuan Zhang, Kaiyuan Tao, Guanhong An, Shengwei Yan, Lu Zhang, Zhuo Ma, Shiqing Zhang, Xiangyu |
| author_facet | Shen, Guangyu Cheng, Siyuan Zhang, Kaiyuan Tao, Guanhong An, Shengwei Yan, Lu Zhang, Zhuo Ma, Shiqing Zhang, Xiangyu |
| contents | Large Language Models (LLMs) have become prevalent across diverse sectors, transforming human life with their extraordinary reasoning and comprehension abilities. As they find increased use in sensitive tasks, safety concerns have gained widespread attention. Extensive efforts have been dedicated to aligning LLMs with human moral principles to ensure their safe deployment. Despite their potential, recent research indicates aligned LLMs are prone to specialized jailbreaking prompts that bypass safety measures to elicit violent and harmful content. The intrinsic discrete nature and substantial scale of contemporary LLMs pose significant challenges in automatically generating diverse, efficient, and potent jailbreaking prompts, representing a continuous obstacle. In this paper, we introduce RIPPLE (Rapid Optimization via Subconscious Exploitation and Echopraxia), a novel optimization-based method inspired by two psychological concepts: subconsciousness and echopraxia, which describe the processes of the mind that occur without conscious awareness and the involuntary mimicry of actions, respectively. Evaluations across 6 open-source LLMs and 4 commercial LLM APIs show RIPPLE achieves an average Attack Success Rate of 91.5\%, outperforming five current methods by up to 47.0\% with an 8x reduction in overhead. Furthermore, it displays significant transferability and stealth, successfully evading established detection mechanisms. The code of our work is available at \url{https://github.com/SolidShen/RIPPLE_official/tree/official} |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_05467 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Rapid Optimization for Jailbreaking LLMs via Subconscious Exploitation and Echopraxia Shen, Guangyu Cheng, Siyuan Zhang, Kaiyuan Tao, Guanhong An, Shengwei Yan, Lu Zhang, Zhuo Ma, Shiqing Zhang, Xiangyu Artificial Intelligence Computation and Language Cryptography and Security Large Language Models (LLMs) have become prevalent across diverse sectors, transforming human life with their extraordinary reasoning and comprehension abilities. As they find increased use in sensitive tasks, safety concerns have gained widespread attention. Extensive efforts have been dedicated to aligning LLMs with human moral principles to ensure their safe deployment. Despite their potential, recent research indicates aligned LLMs are prone to specialized jailbreaking prompts that bypass safety measures to elicit violent and harmful content. The intrinsic discrete nature and substantial scale of contemporary LLMs pose significant challenges in automatically generating diverse, efficient, and potent jailbreaking prompts, representing a continuous obstacle. In this paper, we introduce RIPPLE (Rapid Optimization via Subconscious Exploitation and Echopraxia), a novel optimization-based method inspired by two psychological concepts: subconsciousness and echopraxia, which describe the processes of the mind that occur without conscious awareness and the involuntary mimicry of actions, respectively. Evaluations across 6 open-source LLMs and 4 commercial LLM APIs show RIPPLE achieves an average Attack Success Rate of 91.5\%, outperforming five current methods by up to 47.0\% with an 8x reduction in overhead. Furthermore, it displays significant transferability and stealth, successfully evading established detection mechanisms. The code of our work is available at \url{https://github.com/SolidShen/RIPPLE_official/tree/official} |
| title | Rapid Optimization for Jailbreaking LLMs via Subconscious Exploitation and Echopraxia |
| topic | Artificial Intelligence Computation and Language Cryptography and Security |
| url | https://arxiv.org/abs/2402.05467 |