Formalization Driven LLM Prompt Jailbreaking via Reinforcement Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908562970640384 |
|---|---|
| author | Wang, Zhaoqi He, Daqing Zhang, Zijian Li, Xin Zhu, Liehuang Li, Meng Liu, Jiamou |
| author_facet | Wang, Zhaoqi He, Daqing Zhang, Zijian Li, Xin Zhu, Liehuang Li, Meng Liu, Jiamou |
| contents | Large language models (LLMs) have demonstrated remarkable capabilities, yet they also introduce novel security challenges. For instance, prompt jailbreaking attacks involve adversaries crafting sophisticated prompts to elicit responses from LLMs that deviate from human values. To uncover vulnerabilities in LLM alignment methods, we propose the PASS framework (\underline{P}rompt J\underline{a}ilbreaking via \underline{S}emantic and \underline{S}tructural Formalization). Specifically, PASS employs reinforcement learning to transform initial jailbreak prompts into formalized descriptions, which enhances stealthiness and enables bypassing existing alignment defenses. The jailbreak outputs are then structured into a GraphRAG system that, by leveraging extracted relevant terms and formalized symbols as contextual input alongside the original query, strengthens subsequent attacks and facilitates more effective jailbreaks. We conducted extensive experiments on common open-source models, demonstrating the effectiveness of our attack. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_23558 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Formalization Driven LLM Prompt Jailbreaking via Reinforcement Learning Wang, Zhaoqi He, Daqing Zhang, Zijian Li, Xin Zhu, Liehuang Li, Meng Liu, Jiamou Artificial Intelligence Cryptography and Security Large language models (LLMs) have demonstrated remarkable capabilities, yet they also introduce novel security challenges. For instance, prompt jailbreaking attacks involve adversaries crafting sophisticated prompts to elicit responses from LLMs that deviate from human values. To uncover vulnerabilities in LLM alignment methods, we propose the PASS framework (\underline{P}rompt J\underline{a}ilbreaking via \underline{S}emantic and \underline{S}tructural Formalization). Specifically, PASS employs reinforcement learning to transform initial jailbreak prompts into formalized descriptions, which enhances stealthiness and enables bypassing existing alignment defenses. The jailbreak outputs are then structured into a GraphRAG system that, by leveraging extracted relevant terms and formalized symbols as contextual input alongside the original query, strengthens subsequent attacks and facilitates more effective jailbreaks. We conducted extensive experiments on common open-source models, demonstrating the effectiveness of our attack. |
| title | Formalization Driven LLM Prompt Jailbreaking via Reinforcement Learning |
| topic | Artificial Intelligence Cryptography and Security |
| url | https://arxiv.org/abs/2509.23558 |