arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2510.02422cs.CRcs.AI
收藏

动态目标攻击

Dynamic Jailbreaking Attack

The State Key Laboratory of Blockchain and Data Security, Zhejiang University(区块链与数据安全国家重点实验室,浙江大学);Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security(杭州高新技术区(滨江)区块链与数据安全研究院);Nanyang Technological University(南洋理工大学);King Abdullah University of Science and Technology(国王阿卜杜勒阿齐兹科技大学);SUN YAT-SEN UNIVERSITY(孙中山大学)

Kedong Xiu, Yunhan Yang, Churui Zeng, Tianhang Zheng, Xinzhe Huang, Di Wang, Puning Zhao, Zhan Qin, Kui Ren

AI总结:

动态目标攻击通过利用目标模型自身响应作为自适应目标,提高了对抗攻击的成功率和效率。

摘要:

现有的基于梯度的对抗攻击通常优化一个对抗性后缀以诱导一个固定肯定响应,例如

英文摘要:

Existing gradient-based jailbreak attacks typically optimize a fixed-length adversarial suffix toward a predefined target response with a static optimization strategy. However, this fully static formulation undermines the effectiveness, efficiency and flexibility of gradient-based jailbreaking because (i) A predefined target usually lies in the low-probability region of a safety-aligned LLM's conditional output distribution, forcing the optimization to pursue an unlikely response pattern; (ii) Simple affirmative targets may even mislead LLMs to generate affirmative responses that are not highly relevant to the prompts; (iii) Fixed optimization strategy and suffix length treat all prompts equally, leading to limited attack capability for hard prompts and redundant capacity for easy ones. To address these limitations, we propose Dynamic Jailbreaking Attack (DJA), a parameter-free gradient-based jailbreak framework using dynamic candidate exploration, dynamic relevant targets and dynamic optimization strategy to craft adversarial prompts. In each optimization round, DJA samples multiple candidate target responses directly from the LLM's distribution conditioned on the current adversarial prompt. Among these candidates, DJA employs a multi-objective scorer to select an optimal target that satisfies multi-dimensional criteria such as harmfulness, relevance, and usefulness. Moreover, DJA introduces a parameter-free dynamic optimization strategy that allocates adversarial effort based on real-time feedback, adapting suffix length, candidate sampling capacity, and optimization iterations according to the difficulty of each harmful prompt. In an extensive evaluation of 40 safety-aligned LLMs (12 model families, scaling from 0.5B to 32B), DJA achieves a 100% ASR across all LLMs, requiring only 13.68 optimization rounds on average (10 iterations per round).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑