TrailBlazer: History-Guided Reinforcement Learning for Black-Box LLM Jailbreaking
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910014016323584 |
|---|---|
| author | Yoon, Sung-Hoon Qian, Ruizhi Zhao, Minda Li, Weiyue Wang, Mengyu |
| author_facet | Yoon, Sung-Hoon Qian, Ruizhi Zhao, Minda Li, Weiyue Wang, Mengyu |
| contents | Large Language Models (LLMs) have become integral to many domains, making their safety a critical priority. Prior jailbreaking research has explored diverse approaches, including prompt optimization, automated red teaming, obfuscation, and reinforcement learning (RL) based methods. However, most existing techniques fail to effectively leverage vulnerabilities revealed in earlier interaction turns, resulting in inefficient and unstable attacks. Since jailbreaking involves sequential interactions in which each response influences future actions, reinforcement learning provides a natural framework for this problem. Motivated by this, we propose a history-aware RL-based jailbreak framework that analyzes and reweights vulnerability signals from prior steps to guide future decisions. We show that incorporating historical information alone improves jailbreak success rates. Building on this insight, we introduce an attention-based reweighting mechanism that highlights critical vulnerabilities within the interaction history, enabling more efficient exploration with fewer queries. Extensive experiments on AdvBench and HarmBench demonstrate that our method achieves state-of-the-art jailbreak performance while significantly improving query efficiency. These results underscore the importance of historical vulnerability signals in reinforcement learning-driven jailbreak strategies and offer a principled pathway for advancing adversarial research on LLM safeguards. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_06440 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TrailBlazer: History-Guided Reinforcement Learning for Black-Box LLM Jailbreaking Yoon, Sung-Hoon Qian, Ruizhi Zhao, Minda Li, Weiyue Wang, Mengyu Computation and Language Artificial Intelligence Cryptography and Security Large Language Models (LLMs) have become integral to many domains, making their safety a critical priority. Prior jailbreaking research has explored diverse approaches, including prompt optimization, automated red teaming, obfuscation, and reinforcement learning (RL) based methods. However, most existing techniques fail to effectively leverage vulnerabilities revealed in earlier interaction turns, resulting in inefficient and unstable attacks. Since jailbreaking involves sequential interactions in which each response influences future actions, reinforcement learning provides a natural framework for this problem. Motivated by this, we propose a history-aware RL-based jailbreak framework that analyzes and reweights vulnerability signals from prior steps to guide future decisions. We show that incorporating historical information alone improves jailbreak success rates. Building on this insight, we introduce an attention-based reweighting mechanism that highlights critical vulnerabilities within the interaction history, enabling more efficient exploration with fewer queries. Extensive experiments on AdvBench and HarmBench demonstrate that our method achieves state-of-the-art jailbreak performance while significantly improving query efficiency. These results underscore the importance of historical vulnerability signals in reinforcement learning-driven jailbreak strategies and offer a principled pathway for advancing adversarial research on LLM safeguards. |
| title | TrailBlazer: History-Guided Reinforcement Learning for Black-Box LLM Jailbreaking |
| topic | Computation and Language Artificial Intelligence Cryptography and Security |
| url | https://arxiv.org/abs/2602.06440 |