Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing

Abstract

This paper proposes a guaranteed defense method for large language models (LLMs) to safeguard against jailbreaking attacks. Drawing inspiration from the denoised-smoothing approach in the adversarial defense domain, we propose a novel smoothing-based defense method, termed Disrupt-and-Rectify Smoothing (DR-Smoothing). Specifically, we integrate a two-stage prompt processing scheme-first disrupting the input prompt, then rectifying it-into the conventional smoothing defense framework. This disrup

Categories

Framework mappings

Suggested from the entry's categories.

@misc{lin2026guaranteed,
  title = {{Guaranteed Jailbreaking Defense via Disrupt-and-Rectify Smoothing}},
  author = {Zheng Lin and Zhenxing Niu and Haoxuan Ji and Haichang Gao},
  year = {2026},
  month = may,
  eprint = {2605.10582},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.10582}
}