Foot In The Door: Understanding Large Language Model Jailbreaking via Cognitive Psychology
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910343152795648 |
|---|---|
| author | Wang, Zhenhua Xie, Wei Wang, Baosheng Wang, Enze Gui, Zhiwen Ma, Shuoyoucheng Chen, Kai |
| author_facet | Wang, Zhenhua Xie, Wei Wang, Baosheng Wang, Enze Gui, Zhiwen Ma, Shuoyoucheng Chen, Kai |
| contents | Large Language Models (LLMs) have gradually become the gateway for people to acquire new knowledge. However, attackers can break the model's security protection ("jail") to access restricted information, which is called "jailbreaking." Previous studies have shown the weakness of current LLMs when confronted with such jailbreaking attacks. Nevertheless, comprehension of the intrinsic decision-making mechanism within the LLMs upon receipt of jailbreak prompts is noticeably lacking. Our research provides a psychological explanation of the jailbreak prompts. Drawing on cognitive consistency theory, we argue that the key to jailbreak is guiding the LLM to achieve cognitive coordination in an erroneous direction. Further, we propose an automatic black-box jailbreaking method based on the Foot-in-the-Door (FITD) technique. This method progressively induces the model to answer harmful questions via multi-step incremental prompts. We instantiated a prototype system to evaluate the jailbreaking effectiveness on 8 advanced LLMs, yielding an average success rate of 83.9%. This study builds a psychological perspective on the explanatory insights into the intrinsic decision-making logic of LLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_15690 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Foot In The Door: Understanding Large Language Model Jailbreaking via Cognitive Psychology Wang, Zhenhua Xie, Wei Wang, Baosheng Wang, Enze Gui, Zhiwen Ma, Shuoyoucheng Chen, Kai Computation and Language Artificial Intelligence Large Language Models (LLMs) have gradually become the gateway for people to acquire new knowledge. However, attackers can break the model's security protection ("jail") to access restricted information, which is called "jailbreaking." Previous studies have shown the weakness of current LLMs when confronted with such jailbreaking attacks. Nevertheless, comprehension of the intrinsic decision-making mechanism within the LLMs upon receipt of jailbreak prompts is noticeably lacking. Our research provides a psychological explanation of the jailbreak prompts. Drawing on cognitive consistency theory, we argue that the key to jailbreak is guiding the LLM to achieve cognitive coordination in an erroneous direction. Further, we propose an automatic black-box jailbreaking method based on the Foot-in-the-Door (FITD) technique. This method progressively induces the model to answer harmful questions via multi-step incremental prompts. We instantiated a prototype system to evaluate the jailbreaking effectiveness on 8 advanced LLMs, yielding an average success rate of 83.9%. This study builds a psychological perspective on the explanatory insights into the intrinsic decision-making logic of LLMs. |
| title | Foot In The Door: Understanding Large Language Model Jailbreaking via Cognitive Psychology |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2402.15690 |