研究方向  >> More

多媒体取证
人脸鉴伪技术、主动性深度伪造防御、图像篡改检测等

深度模型安全
对抗样本攻击、后门攻击等

计算机视觉
目标检测、语义分割、水下视觉等

新闻资讯  >> More

• [2024.10]: 祝贺李云飞同学关于序列化深度伪造检测的工作TSOM被知名视觉会议WACV接收.   New!    
• [2024.09]: 祝贺李汉哲同学关于深度伪造检测的工作FreqBlender被机器学习顶会NeurIPS接收.   New!    
• [2024.09]: 祝贺李岳尊博士入选2024全球前2%顶尖科学家榜单.   New!    
• [2024.09]: 祝贺张东亮同学关于深度伪造检测的工作DPL被知名视觉会议ACCV接收.   New!    
• [2024.09]: 祝贺陈增强同学关于深度伪造检测的工作被会议CCBR接收.   New!    
• [2024.07]: 祝贺张迎同学关于图像修复检测的工作Mumpy被知名视觉会议BMVC接收.   New!    
• [2024.07]: 祝贺张仰祥同学关于高效图像篡改检测的工作FastForensics被知名视觉会议BMVC接收.   New!    
• [2024.07]: 一篇关于可迁移深度伪造检测的工作被CCF A类（中科院一区）期刊IEEE TIFS接收.   New!    
• [2024.07]: 一篇关于深度伪造检测的工作被视觉顶会ECCV接收.   New!    
• [2024.05]: 一篇关于多人脸深度伪造检测的工作被CCF B类（中科院一区）期刊IEEE TCSVT接收.   New!    
• [2024.04]: 祝贺陆久翠同学关于深度伪造检测的工作被CCF A类顶级期刊IEEE TIFS接收.   New!    
• [2024.04]: 祝贺于佳傲同学关于图像文本检索的工作被CCF B类会议ACM ICMR接收.   New!    
• [2024.02]: 祝贺于佳傲同学关于图像文本检索的工作被期刊KBS接收.   New!    
• [2024.01]: 一篇关于主动性深度伪造防御的论文被CCF B类期刊CVIU接收.   New!    
• [2023.12]: 一篇关于对抗鲁棒性的论文被CCF B类会议ICASSP接收.  
• [2023.11]: 李岳尊博士在第四届CSIG中国媒体取证与安全大会学术新锐论坛作报告: 深度伪造的检测与防御.  

学术论文  >> More

• Texture, Shape and Order Matter: A New Transformer Design for Sequential DeepFake Detection. Yunfei Li, Yuezun Li^#, Xin Wang, Baoyuan Wu, Jiaran Zhou, Junyu Dong. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024. [CVF之一]
• FreqBlender: Enhancing DeepFake Detection by Blending Frequency Knowledge. Hanzhe Li, Jiaran Zhou, Yuezun Li^#, Baoyuan Wu, Bin Li, Junyu Dong. The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS), 2024. [CCF A]
• DPL: Cross-quality DeepFake Detection via Dual Progressive Learning. Dongliang Zhang, Yunfei Li, Jiaran Zhou, Yuezun Li^#. Asian Conference on Computer Vision (ACCV), 2024. [CCF C, acceptance rate: 32%]
• Enhancing Deepfake Detection via Adversarial Generative Learning. Zengqiang Chen, Xudong Wang, Yuezun Li^#. Chinese Conference on Biometric Recognition (CCBR), 2024.
• FastForensics: Efficient Two-Stream Design for Real-Time Image Manipulation Detection. Yangxiang Zhang, Yuezun Li^#, Ao Luo, Jiaran Zhou, Junyu Dong. British Machine Vision Conference (BMVC), 2024. [CCF C, TH-CPL B, acceptance rate: 25.8%]
• Mumpy: Multilateral Temporal-view Pyramid Transformer for Video Inpainting Detection. Ying Zhang, Yuezun Li^#, Bo Peng, Jiaran Zhou, Huiyu Zhou, Junyu Dong. British Machine Vision Conference (BMVC), 2024. [CCF C, TH-CPL B, acceptance rate: 25.8%]
• DomainForensics: Exposing Face Forgery across Domains via Bi-directional Adaptation. Qingxuan Lv, Yuezun Li^#, Junyu Dong^#, Sheng Chen, Hui Yu, Huiyu Zhou, Shu Zhang. IEEE Transactions on Information Forensics and Security (TIFS), 2024. [CCF A][中科院一区]
• Fake It till You Make It: Curricular Dynamic Forgery Augmentations towards General Deepfake Detection. Yuzhen Lin, Wentang Song, Bin Li, Yuezun Li, Jiangqun Ni, Han Chen, Qiushi Li. European Conference on Computer Vision (ECCV), 2024. [CCF B][视觉顶会]
• COMICS: End-to-end Bi-grained Contrastive Learning for Multi-face Forgery Detection. Cong Zhang, Honggang Qi, Shuhui Wang, Yuezun Li^#, Siwei Lyu. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2024. [CCF B][中科院一区]