Enhancing the Transferability of Jailbreak Attacks on Large Language Models via Exploiting Reparameterization Invariance
Ao Wang, Xinghao Yang, Yongshun Gong, Wei Liu, Bao-di Liu, Weifeng Liu
Abstract
Jailbreak attacks serve as a pivotal technique for evaluating the safety alignment of Large language models. Current token-level attacks have shown remarkable efficacy on open-source models by leveraging gradient-based optimization. However, these attacks suffer from poor cross-model transferability, severely limiting their utility on proprietary ones. To address this limitation, we propose Reparameterization Invariance Gradient-based Jailbreak (RIGJ), a natural gradient based framework designed to improve cross-model transferability. Unlike prior token-level methods whose optimization paths are constrained by model-specific Euclidean geometry, RIGJ defines update directions according to differences in output distributions rather than parameter-space distances. Since language models are trained to capture similar dependency structures of natural language, their output distributions share common geometry across architectures, yielding intrinsically model-agnostic optimization trajectories and substantially stronger jailbreak transferability. Extensive experiments demonstrate superior performance, increasing the cross-model Attack Success Rate and Average Harmfulness Score by 14.9% and 1.23, respectively. Our code is provided in https://github.com/nohuma/AISafety_ transfer_jailbreak_RIGJ_2026 .
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Tree of Attacks: Jailbreaking Black-Box LLMs Automatically cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
- Tree of Attacks: Jailbreaking Black-Box LLMs Automatically cites AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models
- Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To! cites Training language models to follow instructions with human feedback
- AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
- AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models cites Training language models to follow instructions with human feedback
Builds on17
- Training language models to follow instructions with human feedbackLong Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida et al.NeurIPS 2022 · 24,707 citations
- Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!Xiangyu Qi, Yi Zeng, Tinghao Xie, Pin-Yu Chen et al.ICLR 2024 · 1,104 citations
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust RefusalMantas Mazeika, Long Phan, Xuwang Yin, Andy Zou et al.ICML 2024 · 1,031 citations
- Tree of Attacks: Jailbreaking Black-Box LLMs AutomaticallyAnay Mehrotra, Manolis Zampetakis, Paul Kassianik, Blaine Nelson et al.NeurIPS 2024 · 835 citations
- AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language ModelsXiaogeng Liu, Nan Xu, Muhao Chen, Chaowei XiaoICLR 2024 · 722 citations
Related papers
- Guiding not Forcing: Enhancing the Transferability of Jailbreaking Attacks on LLMs via Removing Superfluous ConstraintsJunxiao Yang, Zhexin Zhang, Shiyao Cui, Hongning Wang et al.ACL 2025 · 6 citations
- TAO-Attack: Toward Advanced Optimization-Based Jailbreak Attacks for Large Language ModelsZhi Xu, Jiaqi Li, Xiaotong Zhang, Hong Yu et al.ICLR 2026 · 2 citations
- Attention Eclipse: Manipulating Attention to Bypass LLM Safety-AlignmentPedram Zaree, Md Abdullah Al Mamun, Quazi Mishkatul Alam, Yue Dong et al.EMNLP 2025
- Rewrite to Jailbreak: Discover Learnable and Transferable Implicit Harmfulness InstructionYuting Huang, Chengyuan Liu, Yifeng Feng, Yiquan Wu et al.ACL Findings 2025 · 1 citation
- QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query LanguageQingsong Zou, Jingyu Xiao, Qing Li, Zhi Yan et al.ACL Findings 2025 · 4 citations
