2026 顶会论文
5作者位次 #2/4NeurIPS 2026Poster· Social Aspects / Trustworthy Machine Learning
Exposing Private Corpus Leakage in Multimodal RAG
Yihao LIU · XINQI LYU · Dong Wang · Bin Xiao
一作NeurIPS 2026Poster· Social Aspects / Trustworthy Machine Learning
Train-free Data Poisoning Attack against Retrieval-augmented Diffusion Models
XINQI LYU · Yihao LIU · Yiming Cao · Bin Xiao
作者位次 #3/4CVPR 2026Poster· Computer Vision & Pattern Recognition
Breaking Multimodal LLM Safety via Video-Driven Prompting
Dong Wang · Xiangyu He · XINQI LYU · Bin Xiao
一作CVPR 2026Poster· Computer Vision & Pattern Recognition
Red-teaming Retrieval-Augmented Diffusion Models via Poisoning Knowledge Bases
XINQI LYU · Yihao LIU · Dong Wang · Bin Xiao
作者位次 #3/4CVPR 2026Poster· Computer Vision & Pattern Recognition
PureProof: Diffusion-Resistant Black-box Targeted Attack on Large Vision-Language Models
Yiming Cao · Dong Wang · XINQI LYU · Bin Xiao