AAAI 2026technical0 citations
MAJIC: Markovian Adaptive Jailbreaking via Iterative Composition of Diverse Innovative Strategies
Weiwei Qi, Shuo Shao, Wei Gu, Tianhang Zheng, Puning Zhao, Zhan Qin, Kui Ren
Abstract
Large Language Models (LLMs) have exhibited remarkable capabilities but remain vulnerable to jailbreaking attacks, which can elicit harmful content from the models by manipulating the input prompts. Existing black-box jailbreaking techniques primarily rely on static prompts crafted with a single, non-adaptive strategy, or employ rigid combinations of several underperforming attack methods, which limits their adaptability and generalization. To address these limitations, we propose MAJIC, a Markovian adaptive jailbreaking framework that attacks black-box LLMs by iteratively combining diverse innovative disguise strategies. MAJIC first establishes a
BibTeX
@inproceedings{aaai2026_majicmarkovianad,
title = {MAJIC: Markovian Adaptive Jailbreaking via Iterative Composition of Diverse Innovative Strategies},
author = {Weiwei Qi and Shuo Shao and Wei Gu and Tianhang Zheng and Puning Zhao and Zhan Qin and Kui Ren},
booktitle = {AAAI 2026},
year = {2026}
}