AAAI 2026technical0 citations

MirrorShield: Towards Dynamic Adaptive Defense Against Jailbreaks via Entropy-Guided Mirror Crafting

Rui Pu, Chaozhuo Li, Rui Ha, Litian Zhang, Lirong Qiu, Xi Zhang

Abstract

Defending large language models (LLMs) against jailbreak attacks is crucial for ensuring their safe deployment. Existing defense strategies typically rely on predefined static criteria to differentiate between harmful and benign prompts. However, such rigid rules fail to accommodate the inherent complexity and dynamic nature of real-world jailbreak attacks. In this paper, we focus on the novel challenge of adaptive defense against diverse jailbreaks. We propose a new concept "mirror

BibTeX
@inproceedings{aaai2026_mirrorshieldtowa,
  title = {MirrorShield: Towards Dynamic Adaptive Defense Against Jailbreaks via Entropy-Guided Mirror Crafting},
  author = {Rui Pu and Chaozhuo Li and Rui Ha and Litian Zhang and Lirong Qiu and Xi Zhang},
  booktitle = {AAAI 2026},
  year = {2026}
}
MirrorShield: Towards Dynamic Adaptive Defense Against Jailbreaks via Entropy-Guided Mirror Crafting · AAAI 2026