arXiv cs.CL· Taikun Chen, Yue Zhang, Wei Qian, Hui Fang·· 11 小时前AI 评分31
RL-ATTACK：基于强化学习的语言模型通用黑盒对抗攻击框架
RL-ATTACK: A Generalized Black-Box Adversarial Attack on Language Models via Reinforcement Learning
AI 导读
研究者提出 RL-ATTACK，一种基于强化学习的可训练黑盒对抗攻击框架，从目标模型学习生成定制化对抗变换。在自然语言推理任务上，它能在 20 次查询内将攻击后准确率降至 2%；针对生成式语言模型，其攻击后准确率持续低于未训练攻击者，并在 6 个设置中的 4 个优于强优化基线。该工作已被 IEEE EdgeCom 2026 接收为 regular paper，代码已开源。
正文 · 原文
Abstract:Large language models (LLMs) exhibit vulnerabilities to adversarial perturbations that can induce unintended responses. These vulnerabilities can be identified via intentional attacks and subsequently used to improve model safety. In black-box settings where gradients are inaccessible, existing methods tend to guess adversarial transformations using external knowledge, ignoring the information provided by the target model. To mitigate this, we propose a trainable black-box framework based on reinforcement learning, which learns from the target model to generate tailored adversarial transformations. We demonstrate that our approach achieves lower post-attack accuracy, greater query efficiency and better semantic preservation on both natural language inference and generative Q&A tasks. On natural language inference, it drives post-attack accuracy to 2% within 20 queries. Against generative language models, our trained attacker consistently achieves lower post-attack accuracy than the untrained attacker and wins in 4 out of 6 settings when compared to a strong optimization-based baseline. We further experiment with multiple reward designs and training settings, and we find that no design or setting is consistently dominant. Our code is available at this https URL.
| Comments: | Accepted as a regular paper at IEEE EdgeCom 2026 |
| Subjects: | Computation and Language (cs.CL); Cryptography and Security (cs.CR) |
| Cite as: | arXiv:2611.08711 [cs.CL] |
| (or arXiv:2611.08711v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.08711 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Taikun Chen [view email]
[v1]
Thu, 5 Nov 2026 21:06:21 UTC (960 KB)
来源：arXiv cs.CL · arxiv.org