Jailbreaking LLMs Without Gradients or Priors: Effective and Transferable Attacks

Abstract

As Large Language Models (LLMs) are increasingly deployed in safety-critical domains, rigorously evaluating their robustness against adversarial jailbreaks is essential. However, current safety evaluations often overestimate robustness because existing automated attacks are limited by restrictive assumptions. They typically rely on handcrafted priors or require white-box access for gradient propagation. We challenge these constraints by demonstrating that token-level iterative optimization can succeed without gradients or priors. We introduce RAILS (RAndom Iterative Local Search), a framework that operates solely on model logits. RAILS matches the effectiveness of gradient-based methods through two key innovations: a novel auto-regressive loss that enforces exact prefix matching, and a history-based selection strategy that bridges the gap between the proxy optimization objective and the true attack success rate. Crucially, by eliminating gradient dependency, RAILS enables cross-tokenizer ensemble attacks. This allows for the discovery of shared adversarial patterns that generalize across disjoint vocabularies, significantly enhancing transferability to closed-source systems. Empirically, RAILS achieves near 100% success rates on multiple open-source models and high black-box attack transferability to closed-source systems like GPT and Gemini.