Enhancing the Transferability of Jailbreak Attacks on Large Language Models via Exploiting Reparameterization Invariance
Year: 2026
Type: conference-paper
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.
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166847087