Kunlin Cai
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
ImageAuditor introduces a novel Membership Inference Attack (MIA) specifically designed for Image-based Retrieval-Augmented Generation (IRAG) systems, achieving high accuracy by addressing cross-modal retrieval and discriminative signal extraction challenges.
RogueMerge introduces a unified framework to robustly attack LLM model merging by addressing the challenges of autoregressive decoding, unknown merging configurations, and prompt generalization, significantly outperforming prior methods.
Papers
ImageAuditor: Membership Inference Attack against Image-based Retrieval-Augmented Generation
Jinghuai Zhang, Pengyue Yu, Zhexiao Lin, Kunlin Cai +2 more
ImageAuditor introduces a novel Membership Inference Attack (MIA) specifically designed for Image-based Retrieval-Augmented Generation (IRAG) systems, achieving high accuracy by addressing cross-modal…