一、个人简介
蔡晓雯，河北沧州人，郑州大学助理教授。博士毕业于华中科技大学网络空间安全学院。研究方向包括计算机视觉、人工智能安全。近五年在TAPMI、NeurIPS、ICML、TIFS、ACM MM、EMNLP、PR等国际顶级期刊和会议发表学术论文10余篇。担任NeurIPS、TIFS、AAAI等多个国际顶级期刊和会议审稿人。
二、研究方向
3D点云感知、多模态大模型、大模型攻击与防御
三、代表性论文 (*通讯作者；#共同一作)
[1] Zhenze Yang, Xiaowen Cai*, Junhao Dong, Guangke Chen, Guiyao Tie, Daizong Liu, Hongyang He, Zhiyuan Ma, Xiang Fang, Dengpan Ye, Jing Zhang. Cross-Model Transfer Attacks against Large Vision-Language Models via Model Diversity Enrichment and Stochastic Parameter Sampling.. in: Neural Information Processing Systems. 2026.（CCF A 类会议）
[2] Xiaowen Cai, Daizong Liu, Xiaoye Qu, Xiang Fang, Jianfeng Dong, Keke Tang, Pan Zhou, Lichao Sun, Wei Hu. Towards Building Model/Prompt-Transferable Attackers against Large Vision-Language Models. in: Neural Information Processing Systems. 2025.（CCF A 类会议）
[3] Daizong Liu, Xiaowen Cai#, Pan Zhou, Xiaoye Qu, Lichao Sun, Wei Hu. Are Large Vision-Language Models Robust to Adversarial Visual Transformations? IEEE Transactions on Information Forensics and Security, 2025.（CCF A 类期刊）
[4] Xiaowen Cai, Yunbo Tao, Daizong Liu, Pan Zhou, Xiaoye Qu, Jianfeng Dong, Keke Tang, Lichao Sun. Frequency-aware gan for imperceptible transfer attack on 3d point clouds. in: ACM International Conference on Multimedia. 2024.（CCF A 类会议）
[5] Hai Yan#, Haijian Ma#, Xiaowen Cai#, Daizong Liu, Zenghui Yuan, Xiaoye Qu, Jianfeng Dong, Runwei Guan, Xiang Fang, Hongyang He, Yulai Xie, Pan Zhou. Fit the Distribution: Cross-Image/Prompt Adversarial Attacks on Multimodal Large Language Models. in: Neural Information Processing Systems. 2025.（CCF A 类会议）
[6] Daizong Liu, Tianyao Luo, Junhao Dong, Xiaowen Cai, Hao He, Weidong Wang, Runwei Guan, Jianfeng Dong, Pan Zhou, Bo Du, Hui Xiong. Flexible Targeted Adversarial Alignment with Frequency-based Visual Focus for Attacking Large Vision-Language Models. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026 (CCF A类期刊)
[7] Daizong Liu, Xiaowen Cai, Junhao Dong, Zhongliang Guo, Xiaoye Qu, Runwei Guan, Xiang Fang, Dengpan Ye. Attacking gray-box large vision-language models with adaptive svd-structured adversarial alignment. in: Forty-third International Conference on Machine Learning.2026 (CCF A类会议)
[8] Xiaowen Cai, Daizong Liu, Runwei Guan, Pan Zhou. Imperceptible Transfer Attack on Large Vision-Language Models. in: IEEE International Conference on Acoustics, Speech and Signal Processing. 2025.（CCF B 类会议）
[9] Haijian Ma#, Daizong Liu#, Xiaowen Cai#, Pan Zhou, Yulai Xie. Learning from Few Samples: A Novel Approach for High-Quality Malcode Generation. in: Empirical Methods in Natural Language Processing. 2025.（CCF B 类会议）
四、联系方式
欢迎对科研感兴趣的本科生、硕士生加入课题组学习！
电子邮箱：xiaowencai@zzu.edu.cn
