研究方向与成果

研究方向为多媒态智能处理，人工智能安全与应用，近期研究工作涉及算法安全、内容安全和大模型安全等方面。 研究所技术副总师，科技创新2030“新一代人工智能”重大项目负责人，承担或参与完成国家973、863、国家自然科学基金重大与面上项目等30余项。在TPAMI、TIFS、CVPR、AAAI等期刊和国际会议发表论文百余篇，获得国家发明专利授权20余项，出版译著2部。获中国科学院2023年度优秀导师奖。

• 1.            Yu Cai, Peng Chen, Jiahe Tian, Jin Liu, Jiao Dai, Xi Wang, Shan Jia, Siwei Lyu, Jizhong Han, Modality-Agnostic Deepfakes Detection,            In IH&MMSec 2025 (Best Student Paper)
• 2.            Xiaomeng Fu, Xi Wang, Qiao Li, Jin Liu, Jiao Dai, Jizhong Han, Xingyu Gao, Unlocking Generative Priors: A New Membership Inference Framework for Diffusion Models,            In IEEE TIFS, 2025
• 3.            Shaofei Huang, Rui Ling, Hongyu Li, Tianrui Hui, Zongheng Tang, Xiaoming Wei, Jizhong Han, Si Liu, Unleashing the temporal-spatial reasoning capacity of gpt for training-free audio and language referenced video object segmentation,            In AAAI 2025
• 4.            Shaofei Huang, Zhenwei Shen, Zehao Huang, Yue Liao, Jizhong Han, Naiyan Wang, Si Liu, Anchor3DLane++: 3D Lane Detection via Sample-Adaptive Sparse 3D Anchor Regression,            In TPAMI 2024
• 5.            Chuanpeng Yang, Yaxin Liu, Fuqing Zhu, Jizhong Han, Songlin Hu: Uncertainty-Guided Modal Rebalance for Hateful Memes Detection.            In ACL 2024.
• 6.            Chuanpeng Yang, Fuqing Zhu, Yaxin Liu, Jizhong Han, Songlin Hu: Uncertainty-Aware Cross-Modal Alignment for Hate Speech Detection.            In LREC/COLING 2024.
• 7.            Jiahe Tian, Cai Yu, Xi Wang, Peng Chen, Zihao Xiao, Jizhong Han, Yesheng Chai, Dynamic Mixed-Prototype Model for Incremental Deepfake Detection,            In ACM MM 2024
• 8.            Qiao Li, Xiaomeng Fu, Xi Wang, Jin Liu, Xingyu Gao, Jiao Dai, Jizhong Han, Unveiling structural memorization: Structural membership inference attack for text-to-image diffusion models,            In ACM MM 2024
• 9.            Jiahe Tian, Cai Yu, Xi Wang, Peng Chen, Zihao Xiao, Jiao Dai, Jizhong Han, Yesheng Chai, Real appearance modeling for more general deepfake detection,            In ECCV 2024
• 10.            Cai Yu, Shan Jia, Xiaomeng Fu, Jin Liu, Jiahe Tian, Jiao Dai, Xi Wang, Siwei Lyu, Jizhong Han, Explicit correlation learning for generalizable cross-modal deepfake detection,            In ICME 2024
• 11.            Xiaorong Ma, Jiahe Tian, Yu Cai, Yesheng Chai, Zhaoxing Li, Jiao Dai, Liangjun Zang, Jizhong Han, HIDD: Human-perception-centric Incremental Deepfake Detection,            In ICME 2024
• 12.            Jin Chen, Jiahe Tian, Cai Yu, Xi Wang, Zhaoxing Li, Yesheng Chai, Jiao Dai, Jizhong Han, ConfR: Conflict Resolving for Generalizable Deepfake Detection,            In ICME 2024
• 13.            Jiahe Tian, Peng Chen, Cai Yu, Xiaomeng Fu, Xi , Jiao Dai, Jizhong Han, Learning to discover forgery cues for face forgery detection,            In IEEE TIFS 2024
• 14.            Runze He, Shaofei Huang, Xuecheng Nie, Tianrui Hui, Luoqi Liu, Jiao Dai, Jizhong Han, Guanbin Li, Si Liu, Customize your nerf: Adaptive source driven 3d scene editing via local-global iterative training,            In CVPR 2024
• 15.            Tianrui Hui, Si Liu, Zihan Ding, Shaofei Huang, Guanbin Li, Wenguan Wang, Luoqi Liu, Jizhong Han, Language-Aware Spatial-Temporal Collaboration for Referring Video Segmentation,            In TPAMI 2023.,
• 16.            Shaofei Huang, Zhenwei Shen, Zehao Huang, Zihan Ding, Jiao Dai, Jizhong Han, Naiyan Wang, Si Liu, Anchor3DLane: Learning to Regress 3D Anchors for Monocular 3D Lane Detection,            In CVPR 2023.
• 17.            Tianrui Hui, Zizheng Xun, Fengguang Peng, Junshi Huang, Xiaoming Wei, Xiaolin Wei, Jiao Dai, Jizhong Han, Si Liu, Bridging Search Region Interaction with Template for RGB-T Trackin,            In CVPR 2023.
• 18.            Xiaomeng Fu, Xi Wang, Jin Liu, Shuhui Wang, Jiao Dai, Jizhong Han, CoP: Chain-of-Pose for Image Animation in Large Pose Changes,            In ACM MM 2023
• 19.            Chuanpeng Yang, Fuqing Zhu, Jizhong Han, Songlin Hu, Invariant meets specific: A scalable harmful memes detection framework,            In ACM MM 2023
• 20.            Jin Liu, Xi Wang, Xiaomeng Fu, Yesheng Chai, Cai Yu, Jiao Dai, Jizhong Han, Mfr-net: Multi-faceted responsive listening head generation via denoising diffusion model,            In ACM MM 2023