李晟
副教授
复旦大学计算机科学技术学院
邮箱: lisheng [at] fudan.edu.cn
[English]

个人简介：复旦大学计算机学院副教授、博导。主要研究方向为多媒体内容安全、人工智能安全，在知名国际期刊和会议如IEEE TPAMI、IEEE TIP、IEEE TIFS、IEEE TDSC、NDSS、NeurIPS、CVPR、ICCV等发表论文 100 余篇。获得了上海市科技进步二等奖、中国科技产业化促进会科技创新二等奖，以及IEEE WIFS、IEEE MMSP、世界人工智能大会等多个会议的最佳论文奖或提名奖。主持了国家自然科学基金面上/青年项目、国家重点研发计划子课题、国家自然科学基金重点项目子课题等国家级项目，以及上海市青年科技英才扬帆计划、阿里巴巴创新研究计划、CCF-蚂蚁专项基金等省部级和企业合作项目，研究成果被IEEE Spectrum等国际知名科技媒体专题报道。

研究方向

论文成果

corresponding author*, equal contribution#

期刊 (部分)

  1. X. Hu, S. Li, Q. Ying, W. Peng, X. Zhang and Z. Qian, Establishing Robust Generative Image Steganography via Popular Stable Diffusion, IEEE Transactions on Information Forensics and Security, too appear.
  2. Z. Wang, S. Li, X. Zhang and G. Feng, Exploring Abnormal Behavior in Swarm: Identify User Using Adversarial Examples, IEEE Transactions on Emerging Topics in Computational Intelligence, vol. 7, no. 1, pp. 250-260, Feb. 2023.
  3. W. Peng, S. Li, Z. Qian and X. Zhang, Text Steganalysis Based on Hierarchical Supervised Learning and Dual Attention Mechanism, IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 31, pp. 3513-3526, 2023.
  4. Q. Wang, S. Li, Z. Wang, X. Zhang and G. Feng, Multi-source Style Transfer via Style Disentanglement Network, IEEE Transactions on Multimedia, doi: 10.1109/TMM.2023.3281087.
  5. Q. Ying, H. Zhou, Z. Qian, S. Li and X. Zhang, Learning to Immunize Images for Tamper Localization and Self-Recovery, IEEE Transactions on Pattern Analysis and Machine Intelligence, doi: 10.1109/TPAMI.2023.3301958.
  6. S. Li, Z. Wang, X. Zhang and X. Zhang, Robust Image Steganography Against General Downsampling Operations with Lossless Secret Recovery, IEEE Transactions on Dependable and Secure Computing, doi: 10.1109/TDSC.2023.3253691.
  7. Z. Zhu, P. Wei, Z. Qian, S. Li*, X. Zhang, Image Sanitization in Online Social Networks: A General Framework for Breaking Robust Information Hiding, IEEE Transactions on Circuits and Systems for Video Technology, to apprear.
  8. Y. Qiu, Q. Ying, Y. Yang, H. Zeng, S. Li*, Z. Qian*, High-Capacity Framework for Reversible Data Hiding in Encrypted Image Using Pixel Prediction and Entropy Encoding, IEEE Transactions on Circuits and Systems for Video Technology, doi: 10.1109/TCSVT.2022.3163905.
  9. Q. Wang, S. Li, X. Zhang and G. Feng, Multi-granularity Brushstrokes Network for Universal Style Transfer, ACM Transactions on Multimedia Computing, Communications, and Applications, vol. 18, issue. 4, no. 107, pp. 1-17, 2022.
  10. W. Huan, S. Li*, Z. Qian* and X. Zhang, Exploring Stable Coefficients on Joint Sub-bands for Robust Video Watermarking in DT CWT Domain, IEEE Transactions on Circuits and Systems for Video Technology, vol. 32, no. 4, pp. 1955-1965, April 2022.
  11. X. Zhu, S. Li*, X. Zhang, H. Li, and A. C. Kot, Detection of Spoofing Medium Contours for Face Anti-spoofing, IEEE Transactions on Circuits and Systems for Video Technology, vol. 31, no. 5, pp. 2039-2045, 2021.
  12. G. Feng, X. Zhang, Y. Ren, Z. Qian, and S. Li*, Diversity-based Cascade Filters for JPEG Steganalysis, IEEE Transactions on Circuits and Systems for Video Technology, vol. 30, no. 2, pp. 376-386, 2020. (ESI highly cited)
  13. S. Li*, X. Zhang, Z. Qian, G. Feng and Y. Ren, Key Based Artificial Fingerprint Generation for Privacy Protection, IEEE Transactions on Dependable and Secure Computing, vol. 17, no. 4, pp. 828-840, 1 July-Aug. 2020.
  14. S. Li* and X. Zhang, Toward Construction Based Data Hiding: From Secrets to Fingerprint Images, IEEE Transactions on Image Processing, vol. 28, no. 3, pp. 1482-1497, March 2019. (ESI highly cited) [Reported by IEEE Spectrum]
  15. J. Tao, S. Li*, X. Zhang and Z. Wang, Towards Robust Image Steganography, IEEE Transactions on Circuits and Systems for Video Technology, vol. 29, no. 2, pp. 594-600, Feb. 2019. (ESI highly cited)
  16. Y. Wang, S. Li, and A. C. Kot, On Branded Handbag Recognition, IEEE Transactions on Multimedia, 18 (9), pp. 1869-1881, 2016.
  17. Y. Wang, S. Li, and A. C. Kot, Deepbag: Recognizing Handbag Models, IEEE Transactions on Multimedia, 17 (11), pp. 2072-2083, 2015.
  18. S. Li and A. C. Kot, Fingerprint Combination for Privacy Protection, IEEE Transactions on Information Forensics and Security, 8 (2), pp. 350-360, 2013.
  19. S. Li and A. C. Kot, An Improved Scheme for Full Fingerprint Reconstruction, IEEE Transactions on Information Forensics and Security, 7 (6), pp. 1906 – 1912, 2012.
  20. S. Li and A. C. Kot, Privacy Protection of Fingerprint Database, IEEE Signal Processing Letters, 18 (2), pp. 115-118, 2011.

会议 (部分)

  1. J. Huang, Z. Guo, G. Luo, Z. Qian, S. Li, and X. Zhang, Disentangled Style Domain for Implicit z-Watermark Towards Copyright Protection, The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS), 2024.
  2. M. Wang, G. Hua, S. Li*, and G. Feng, A Key-Driven Framework for Identity-Preserving Face Anonymization, Network and Distributed System Security Symposium (NDSS), 2025.
  3. G. Luo, Y. Ma, M. Zhang, J. Huang, S. Li, Z. Qian, X. Zhang, Engaging Live Video Comments Generation, ACM International Conference on Multimedia (MM)，2024.
  4. X. Mao, X. Hu, W. Peng, Z. Gan, Z. Qian, X. Zhang, S. Li, From Covert Hiding To Visual Editing: Robust Generative Video Steganography, ACM International Conference on Multimedia (MM)，2024.
  5. G. Li, S. Li*, Z. Qian, X. Zhang, Cover-separable Fixed Neural Network Steganography via Deep Generative Models, ACM International Conference on Multimedia (MM)，2024.
  6. X. Liu, Y. Yang, H. Wang, Q. Ying, Z. Qian, X. Zhang, S. Li, Multi-view Feature Extraction via Tunable Prompts is Enough for Image Manipulation Localization, ACM International Conference on Multimedia (MM)，2024.
  7. J. Li, H. Wang, S. Li*, Z. Qian, X. Zhang, A. Vasilakos, Are handcrafted filters helpful for attributing AI-generated images?, ACM International Conference on Multimedia (MM)，2024.
  8. G. Li#, S. Li#, Z. Luo, Z. Qian and X. Zhang. Purified and Unified Steganographic Network, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024.
  9. Q. Ying, J. Liu, S. Li*, H. Xu, Z. Qian* and X. Zhang,RetouchingFFHQ: A Large-scale Dataset for Fine-grained Face Retouching Detection, ACM International Conference on Multimedia (MM), 2023.
  10. Z. Luo, S. Li*, G. Li, Z. Qian and X. Zhang, Securing Fixed Neural Network Steganography, ACM International Conference on Multimedia (MM)，2023.
  11. H. Wang, S. Li*, S. Cao, R. Yang, J. Zeng, Z. Qian and X. Zhang, On Physically Occluded Fake Identity Document Detection, ACM International Conference on Multimedia (MM), 2023.
  12. Q. Wang, S. Li*, X. Zhang and G. Feng*, Rethinking Neural Style Transfer: Generating Personalized and Watermarked Stylized Images, ACM International Conference on Multimedia (MM), 2023.
  13. M. Zhang, G. Luo, Y. Ma, S. Li, Z. Qian and X. Zhang, VCMaster: Generating Diverse and Fluent Live Video Comments Based on Multimodal Contexts, ACM International Conference on Multimedia (MM), 2023.
  14. G. Liu, Y. Si, Z. Qian, X. Zhang, S. Li and Wanli Peng “WRAP: Watermarking Approach Robust Against Film-coating upon Printed Photographs,” ACM International Conference on Multimedia (MM), 2023.
  15. J. Tan, N. Zhong, Z. Qian, X. Zhang and S. Li, Deep Neural Network Watermarking against Model Extraction Attack, ACM International Conference on Multimedia (MM), 2023.
  16. X. Hu, Q. Ying, Z. Qian, S. Li and X. Zhang, DRAW: Defending Camera-shooted RAW against Image Manipulation, IEEE/CVF International Conference on Computer Vision (ICCV), 2023.
  17. G. Luo, M. Zhang, Y. Ma, S. Li, Z. Qian and X. Zhang, Forward Creation, Reverse Selection: Achieving Highly Pertinent Multimodal Responses in Dialogue Context, ACM International Conference on Information & Knowledge Management (CIKM), 2023.
  18. G. Li, S. Li*, M. Li, X. Zhang*, Z. Qian, Steganography of Steganographic Networks, AAAI, 2023.
  19. Z. Yuan, Z. You, S. Li*, Z. Qian*, X. Zhang, and A. C. Kot, On Generating Identifiable Virtual Faces, ACM International Conference on Multimedia (MM), 2022 (oral).
  20. Z. You, Q. Ying, S. Li*, Z. Qian*, and X. Zhang, Image Generation Network for Covert Transmission in Online Social Network, ACM International Conference on Multimedia (MM), 2022.
  21. P. Wei, S. Li, X. Zhang, Z. Qian, G. Luo, and Q. Zhou, Generative Steganography Network, ACM International Conference on Multimedia (MM), 2022.
  22. B. Zhang, S. Li*, G. Feng, X. Zhang, and Z. Qian, Patch Diffusion: A General Module for Face Manipulation Detection, AAAI, 2022.
  23. L. Feng, S. Li, Z. Qian, and X. Zhang, Unlabeled Backdoor Poisoning in Semi-Supervised Learning, IEEE International Conference on Multimedia(ICME), 2022.
  24. P. Wei, G. Luo, Q. Song, X. Zhang, Z. Qian, and S. Li, Generative Steganographic Flow, IEEE International Conference on Multimedia (ICME), 2022.
  25. K. Chen, X. Zeng, Q. Ying, S. Li, Z. Qian, and X. Zhang, Invertible Image Dataset Protection, IEEE International Conference on Multimedia (ICME), 2022.
  26. G. Li, S. Li*, Z. Qian, and X. Zhang, Encryption Resistant Deep Neural Network Watermarking, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022.
  27. S. Qi, S. Li, P. Wei, L. Ge, X. Zhang, Z. Qian, Joint Learning for Addressee Selection and Response Generation in Multi-Party Conversation, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022.
  28. L. Feng, S. Li, Z. Qian and X. Zhang, Stealthy Backdoor Attack with Adversarial Training, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022.
  29. G. Luo, P. Wei, S. Zhu, X. Zhang, Z. Qian and S. Li, Image Steganalysis with Convolutional Vision Transformer, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022.
  30. M. Li, N. Zhong, X. Zhang, Z. Qian and S. Li, Object-Oriented Backdoor Attack Against Image Captioning, IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2022.
  31. S. Li, X. Zhu, G. Feng, X. Zhang and Z. Qian, Diffusing the Liveness Cues for Face Anti-spoofing, ACM International Conference on Multimedia (MM), 2021.
  32. Z. You, S. Li, Z. Qian* and X. Zhang, Reversible Privacy-Preserving Recognition, IEEE International Conference on Multimedia and Expo (ICME), 2021.
  33. M. Shi, S. Li, Z. Yin, X. Zhang* and Z. Qian, On Generating JPEG Adversarial Images, IEEE International Conference on Multimedia and Expo (ICME), 2021.
  34. H. Zhan, S. Li and A. C. Kot, Tagging the Shoe Images by Semantic Attributes, IEEE International Conference on Digital Signal Processing (DSP), Singapore, 2015, pp. 892-895.
  35. Y. Wang, S. Li and A. C. Kot, Quality Guided Handbag Segmentation, IEEE International Conference on Digital Signal Processing (DSP), Singapore, 2015, pp. 896-900.
  36. Y. Wang, S. Li and A. C. Kot, Joint Learning for Image-based Handbag Recommendation, IEEE International Conference on Multimedia and Expo (ICME), Turin, 2015, pp. 1-6.
  37. Y. Wang, S. Li and A. C. Kot, Complementary Feature Extraction for Branded Handbag Recognition, IEEE International Conference on Image Processing (ICIP), Paris, 2014, pp. 5896-5900.
  38. S. Li* and A. C. Kot, Attack Using Reconstructed Fingerprint, IEEE International Workshop on Information Forensics and Security (WIFS), Iguacu Falls, 2011, pp. 1-6. [Best Student Paper Silver Award]
  39. S. Li* and A. C. Kot, Privacy Protection of Fingerprint Database Using Lossless Data Hiding, IEEE International Conference on Multimedia and Expo (ICME), Suntec City, 2010, pp. 1293-1298.

Back

科研项目

xxxx虚假证件检测 阿里巴巴创新研究计划 项目负责人 2022.3-2023.3
产品外包装水印 上海驰亚科技 项目负责人 2022.1-2022.7
人工智能模型安全和测试方法 国家自然基金联合重点项目 子课题负责人 2021.1-2023.12
面向社交网络的稳健数字图像隐写 国家自然科学基金面上项目 项目负责人 2021.1-2023.12
xxx保护方法 国家重点研发计划 子课题负责人 2019.7-2022.6
基于信息隐藏的生物特征保护 广西多源数据挖掘与安全实验室重点基金 项目负责人 2019.1-2021.12
面向指纹载体的信息隐藏和伪装 国家自然科学基金青年项目 项目负责人 2017.1-2019.12
生物特征伪装技术研究 上海市科委扬帆计划 项目负责人 2016.6-2019.5

Back

学术任职

International Journal Guest Editor：

  1. Mathematical Methods Applied in Explainable Fake Multimedia Detection, Mathematics, 2022 (Lead Guest Editor)
  2. Low complexity methods for multimedia security, Multimedia Systems, 2019
  3. Recent Advances in Deep Learning Model Security, Pattern Recognition Letters, 2021

Reviewer：

  1. IEEE Transactions on Pattern Analysis and Machine Intelligence
  2. IEEE Transactions on Image Processing
  3. IEEE Transactions on Information Forensics and Security
  4. IEEE Transactions on Multimedia
  5. IEEE Transactions on Neural Networks and Learning Systems
  6. IEEE Signal Processing Letters
  7. EURASIP Journal on Advances in Signal Processing
  8. IEEE International Conference on Image Processing
  9. IEEE International Conference on Multimedia and Expo

Back

学术奖项

Toward Construction Based Data Hiding: From Secrets to Fingerprint Images World Artificial Intelligence Conference, Best paper nomination 2022
Shanghai Young Oriental Scholar 2015
Attack Using Reconstructed Fingerprint IEEE WIFS Best Student Paper Silver Award 2011
Steganograph based on Tolerable Error Range NCIG Best Student Paper Award 2006

Back