硕士生导师
张杰 副研究员 (Associate Professor)
电子邮箱: zhangjie@ict.ac.cn;jie.zhang@vipl.ict.ac.cn
通讯地址:
研究方向: 计算机视觉,模式识别,机器学习
个人简介

张杰,中国科学院计算技术研究所副研究员、硕导,主要从事智能算法安全、算法攻防、后门攻击与防御等基础研究和应用研究。主持中国科学院先导B课题、科技部青年科学家课题、基金委面上、青基等项目,在知名期刊和会议TPAMI、IJCV、TIP、TIFS、ICCV、CVPR等上发表论文30余篇,Google学术引用2500余次(2024.7),授权专利8项,获国际竞赛1次冠军,4次亚军;部分成果在华为多款手机、平安多款人脸识别产品、高铁动车组故障监测、工业视觉检测设备中得到规模化应用,连续两年荣获华为优秀合作奖。先后入选了北京市科技新星计划、中科院青促会和MSRA“铸星计划”。长期担任TPAMI,IJCV,TIP,TMM,TNNLS,TCSVT,CVPR,ICCV,ECCV,NeurIPS,ICLR等领域知名国际期刊和会议的审稿人。


近五年承担参与项目的情况:

(1)  科技部重点研发计划-青年科学家项目,名称:基于DNA的生物物证来源人脸部表征遗传推测技术研究;编号:2021YFC3310100;经费(子课题):180万元;执行期:2021.11-2024.12;课题负责人

(2)  中国科学院先导B课题,名称:算法滥用检测与评估;编号:XDB0680202;经费:1258.63万;执行期:2023.12-2028.11;课题负责人

(3)  网安中心项目,名称:面向多模态信息的智能推荐安全风险评价关键技术研究;经费:135万元;编号:2023-研一-1359;执行期:2023.12-2024.12;项目负责人

(4)  北京市科技新星项目,名称:安全可靠的视觉感知研究;编号:20230484368经费:40万元;执行期:2023.10-2026.10;项目负责人

(5)  NSFC面上项目,名称:面向图像分割的弱监督方法与技术研究;项目编号:62176251;执行周期:2022.01-2025.12;经费:57万元;项目负责人

(6)  NSFC青年项目,名称:面向物体检测的弱监督方法与技术研究;编号:61806188,经费27万,执行期:2019.01-2021.12;项目负责人

(7)  科技部重点研发计划项目子课题,名称:动态生物特征识别系统测评方法研究;编号:2017YFC0821604;经费(子课题):38万元;执行期:2018.06-2022.12;子课题负责人

(8)  科技部重点研发计划课题,名称:复杂样本条件下的深度学习方法与技术;编号:2017YFA0700804;经费:426万元;执行期:2018.5-2023.4;课题骨干


研究生招生:

通常每年秋季招收1名硕士生,欢迎有计算机视觉、深度学习、智能算法安全基础的同学前来客座! 

For more information, please refer to https://jiezhang010.github.io/


经历

教育经历

2007.09-2011.07 中国地质大学(武汉) 软件工程 学士

2011.09-2017.07 中科院计算所 计算机应用技术 博士

学术经历

2019.09至今 中国科学院计算技术研究所,副研究员

2017.07-2019.09 中国科学院计算技术研究所,助理研究员


学术服务

刊物服务

长期担任TPAMI,IJCV,TIP,TMM,TNNLS,TCSVT,PR,TITS, Neural Networks, Information Sciences, Information Fusion, Computers & Security, Expert Systems With Applications, Knowledge-Based Systems, Neurocomputing等期刊审稿人

会议服务

长期担任CVPR,ICCV,ECCV,NeurIPS,ICLR等会议审稿人

研究内容

1.    对抗攻击与防御

2.    后门攻击与检测

3.    分布外泛化与检测

4.    算法公平性、隐私泄露评估与加固

5.    价值观偏离度量与对齐

6.    伪造人脸检测与溯源、活体检测

著论

论文

[TPAMI 2024] Zheng Yuan, Jie Zhang*, Zhaoyan Jiang, Liangliang Li, Shiguang Shan. "Adaptive Perturbation for Adversarial Attack," IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) , 2024.

[IJCV 2024] Zheng Yuan, Jie Zhang*, Yude Wang, Shiguang Shan, Xilin Chen. Towards Robust Semantic Segmentation against Patch-based Attack via Attention Refinement. International Journal of Computer Vision (IJCV), 2024.

[TIP 2024]Mingjie He, Jie Zhang, Shiguang Shan*, Xilin Chen. " Enhancing Face Recognition with Detachable Self-Supervised Bypass Networks," IEEE Transactions on Image Processing (TIP), vol. 33, pp. 1588 – 1599, 2024.

[CVPR 2024] SiboWang, Jie Zhang, Zheng Yuan, Shiguang Shan. “Pre-trained Model Guided Fine-Tuning for Zero-Shot Adversarial Robustness,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.

[CVPR 2024] Zonghui Guo, Xinyu Han, Jie Zhang, Shiguang Shan, Haiyong Zheng. “Video Harmonization with Triplet Spatio-Temporal Variation Patterns,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2024.

[ECCV 2024] Zhongqi Wang, Jie Zhang, Shiguang Shan, Xilin Chen. T2IShield: Defending Against Backdoors on Text-to-Image Diffusion Models. European Conference on Computer Vision (ECCV), 2024.

[CVIU 2024] Changzhen Li, Jie Zhang*, Shuzhe Wu, Xin Jin, Shiguang Shan. "Hierarchical Compositional Representations for Few-shot Action Recognition," Computer Vision and Image Understanding (CVIU), vol. 240, pp. 103911, 2024.

[TIP 2023] Yude Wang, Jie Zhang, Meina Kan, Shiguang Shan, Xilin Chen. "BLPSeg: Balance the Label Preference in Scribble-Supervised Semantic Segmentation," IEEE Transactions on Image Processing (TIP), vol. 32, pp. 4921-4934, 2023.

[TIFS 2023] Xingming Long, Jie Zhang, Shuzhe Wu, Xin Jin, Shiguang Shan*. "Dual Sampling Based Causal Intervention for Face Anti-Spoofing with Identity Debiasing," IEEE Transactions on Information Forensics and Security (TIFS), vol. 19, pp. 851-862, 2023.

[MM 2023] Qiankun Li, Xiaolong Huang, Zhifan Wan, Lanqing Hu, Shuzhe Wu, Jie Zhang, Shiguang Shan, Zengfu Wang. "Data-efficient Masked Video Modeling for Self-supervised Action Recognition," ACM International Conference on Multimedia (ACM MM), pp. 2723-2733, 2023.

[CVPR 2022] Mingjie He, Jie Zhang, Shiguang Shan, Xilin Chen. "Enhancing Face Recognition With Self-Supervised 3D Reconstruction," IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4062-4071, 2022.

[PR 2022]Yude Wang, Jie Zhang*, Meina Kan, Shiguang Shan. " Learning Pseudo Labels for Semi-and-weakly Supervised Semantic Segmentation," Pattern Recognition (PR), vol. 132, pp. 108925, 2022.

[ECCV 2022] Zheng Yuan, Jie Zhang, Shiguang Shan. "Adaptive Image Transformations for Transfer-Based Adversarial Attack," European Conference on Computer Vision (ECCV), pp. 1-17, 2022.

[TIP 2021] Mingjie He, Jie Zhang, Shiguang Shan*, Xiao Liu, Zhongqin Wu, Xilin Chen. "Locality-aware Channel-wise Dropout for Occluded Face Recognition," IEEE Transactions on Image Processing (TIP), vol. 31, pp. 788-798, 2021.

[TIFS 2021] Yunpei Jia, Jie Zhang*, Shiguang Shan. "Dual-branch Meta-learning Network with Distribution Alignment for Face Anti-spoofing," IEEE Transactions on Information Forensics and Security (TIFS), vol. 17, pp. 138-151, 2021.

[ICCV 2021] Zheng Yuan, Jie Zhang, Yunpei Jia, Chuanqi Tan, Tao Xue, Shiguang Shan. " Meta Gradient Adversarial Attack," IEEE/CVF International Conference on Computer Vision (ICCV), pp. 7748-7757, 2021.

[PR 2021] Yunpei Jia, Jie Zhang, Shiguang Shan*, Xilin Chen. "Unified Unsupervised and Semi-supervised Domain Adaptation Network for Cross-scenario Face Anti-spoofing," Pattern Recognition (PR), vol.115, pp. 107888, 2021.

[CVPR 2020] Yude Wang, Jie Zhang, Meina Kan, Shiguang Shan, Xilin Chen. "Self-Supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentation," IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12272-12281, 2020.

[CVPR 2020] Yunpei Jia, Jie Zhang, Shiguang Shan, Xilin Chen. "Single-side Domain Generalization for Face Anti-spoofing," IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8484-8493, 2020.

[PR 2018] Mingjie He, Jie Zhang, Shiguang Shan*, Meina Kan, Xilin Chen. " Deformable Face Net for Pose Invariant Face Recognition," Pattern Recognition (PR), vol.100, pp. 107113, 2018.

[CVPR 2016] Jie Zhang, Meina Kan, Shiguang Shan, and Xilin Chen. "Occlusion-free Face Alignment: Deep Regression Networks Coupled with De-corrupt AutoEncoders," IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3428-3437, 2016.

[ICCV 2015] Jie Zhang, Meina Kan, Shiguang Shan, and Xilin Chen. "Leveraging Datasets With Varying Annotations for Face Alignment via Deep Regression Network," IEEE International Conference on Computer Vision (ICCV), pp. 3801-3809, 2015.

[ECCV 2014] Jie Zhang, Shiguang Shan, Meina Kan, and Xilin Chen. "Coarse-to-Fine Auto-encoder Networks (CFAN) for Real-time Face Alignment," European Conference on Computer Vision (ECCV), pp. 1-16, 2014.