李梓強，省雙創博士，南京信息工程大學副教授。博士畢業於中國科學技術大學。2024年7月加入南京信息工程大學。研究方向包括人工智慧內容生成（AIGC）、人工智慧安全、多媒體內容安全，大模型安全。主持國家自然科學基金青年基金、江蘇省自然科學基金青年基金等項目3項。 以第一作者或共同一作在人工智慧領域頂級會議期刊ICLR、NeurIPS、ECCV、ACM MM、IJCV、TIFS、TDSC、CSUR，上發表相關研究論文數篇。擔任ICLR、NeurIPS 等頂會Area Chair，並長期擔任ICLR、NeurIPS、CVPR、ICCV、ECCV、TPAMI、TIFS、TDSC等國際會議期刊審稿人。
個人簡介,研究方向,科研成果,科研項目,科研獎勵,
個人簡介
李梓強，省雙創博士，南京信息工程大學副教授。博士畢業於中國科學技術大學。2024年7月加入南京信息工程大學。研究方向包括人工智慧內容生成（AIGC）、人工智慧安全、多媒體內容安全，大模型安全。主持國家自然科學基金青年基金、江蘇省自然科學基金青年基金等項目3項。 以第一作者或共同一作在人工智慧領域頂級會議期刊ICLR、NeurIPS、ECCV、ACM MM、IJCV、TIFS、TDSC、CSUR，上發表相關研究論文數篇。擔任ICLR、NeurIPS 等頂會Area Chair，並長期擔任ICLR、NeurIPS、CVPR、ICCV、ECCV、TPAMI、TIFS、TDSC等國際會議期刊審稿人。
研究方向
主要研究方向包括：後門攻擊、生成式內容（圖像、文本）檢測、大模型套用及其安全。
科研成果
*表示共同一作；表示通訊作者。
- 2026:
【1】Yi Wu, Shengju Qian, Lingting Zhu, Lei Liu, Wandi Qiao, Ziqiang Li, Lequan Yu, Bin Li . Proxy-Tuning: Tailoring Multimodal Autoregressive Models for Subject-Driven Image Generation. CVPR, 2026. (CCF-A, 計算機視覺三大頂會).
【2】Jun Li (聯合指導學生), Lizhi Xiong, Ziqiang Li, Weiwei Jiang, Zhangjie Fu, Yong Li, Guo-Sen Xie. Beyond Text Prompts: Precise Concept Erasure through Text–Image Collaboration. CVPR, 2026. (CCF-A, 計算機視覺三大頂會).
【3】Lizhi Xiong, Jun Li, Ziqiang Li, Weiwei Jiang, Zhangjie Fu. No Way To Steal My Face: Proactive Defense Against Identity-Preserving Personalized Generation. CVPR, 2026. (CCF-A, 計算機視覺三大頂會).
【4】Lizhi Xiong, Jianguo Feng, Ziqiang Li, Jun Li, Weiwei Jiang, Zhangjie Fu. NSGuard: Null-Space Guided Robust Watermarking for Data Copyright Protection in Customized Generation. CVPR (Findings), 2026.
【5】Jiazhen Yan (聯合指導學生), Ziqiang Li, Fan Wang, Ziwen He, Zhangjie Fu. Dual Frequency Branch Framework with Reconstructed Sliding Windows Attention for AI-Generated Image Detection. IEEE Transactions on Information Forensics and Security, 2026. (CCF-A, IF:6.3, 中科院 1 區 Top, JCR Q1).
- 2025:
【1】Ziqiang Li, Yueqi Zeng, Pengfei Xia, Lei Liu, Zhangjie Fu, Bin Li. Large Language Models are Good Attackers: Efficient and Stealthy Textual Backdoor Attacks. Pattern Recognition, 2025. (CCF-B, IF:7.6, 中科院 1 區 Top, JCR Q1).
【2】Ziqiang Li, Jiazhen Yan, Ziwen He, Kai Zeng, Weiwei Jiang, Lizhi Xiong, Zhangjie Fu. Is Artificial Intelligence Generated Image Detection a Solved Problem? NeurIPS, 2025. (CCF-A, 機器學習三大頂會).
【3】Ziqiang Li, Pengfei Xia, Hong Sun, Yueqi Zeng, Wei Zhang, and Bin Li. Explore the Effect of Data Selection on Poison Efficiency in Backdoor Attacks. IEEE Transactions on Dependable and Secure Computing, 2025. (CCF-A, IF:7.5, 中科院 1 區 Top, JCR Q1).
【4】Fan Wang, Zhangjie Fu, Xiang Zhang, Ziqiang Li, Ziwen He, Manyu Wang. Pair-wise Confidence Difference-based Pseudo-Label Selection for Universal Mismatched Steganalysis. ACM Multimedia, 2025. (CCF-A, 多媒體頂會).
【5】Lizhi Xiong, Linsen Ding, Ziqiang Li. Detecting Forged HEVC Videos via Anomalous Bitrate-Compressed Traces: A Frame-Level Bitrate Analysis Framework. ACM Multimedia, 2025. (CCF-A, 多媒體頂會).
【6】Beijing Chen, Yuting Hong, Ziqiang Li, Zhangjie Fu. DFPD: Dual-Forgery Proactive Defense against Both Deepfakes and Traditional Image Manipulations. ACM Multimedia, 2025. (CCF-A, 多媒體頂會).
- 2024:
【1】Ziqiang Li, Chaoyue Wang, Xue Rui, Chao Xue, Jiaxu Leng, ZhangJie Fu, Bin Li. Peer is Your Pillar: A Data-unbalanced Conditional GANs for Few-shot Image Generation. IEEE Transactions on Circuits and Systems for Video Technology, 2024. (ESI高被引, CCF-B, IF:8.3, 中科院 1 區 Top, JCR Q1).
【2】Ziqiang Li*, Yi Wu*, Chaoyue Wang, Xue Rui, Bin Li. One-shot Generative Docmain Adaptation in 3D GANs. International Journal of Computer Vision, 2024. (CCF-A, IF:11.6, 中科院 2 區 Top, JCR Q1).
【3】Ziqiang Li, Hong Sun, Pengfei Xia, Beihao Xia, Xue Rui, Wei Zhang, Qinglang Guo, Zhangjie Fu, Bin Li. A Proxy Attack-Free Strategy for Practically Improving the Poisoning Efficiency in Backdoor Attacks. IEEE Transactions on Information Forensics and Security, 2024. (CCF-A, IF:6.3, 中科院 1 區 Top, JCR Q1).
【4】Yi Wu*, Ziqiang Li*, Heliang Zheng, Chaoyue Wang, and Bin Li. Infinite-ID: Identity-preserved Personalization via ID-semantics Decoupling Paradigm. ECCV 2024 (CCF-B, 計算機視覺三大頂會).
【5】Ziqiang Li*, Hong Sun*, Pengfei Xia, Heng Li, Beihao Xia, Yi Wu, and Bin Li. Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios. ICLR 2024 (CCF-A, 機器學習三大頂會).
- 2023:
【1】Ziqiang Li, Muhammad Usman, Rentuo Tao, Pengfei Xia, Chaoyue Wang, Huanhuan Chen, Bin Li. A Systematic Survey of Regularization and Normalization in GANs. ACM Computing Survey, 2023. (IF:23.8, 中科院 1 區 Top, JCR Q1).
【2】Ziqiang Li, Pengfei Xia, Xue Rui, and Bin Li. Exploring the Effect of High-frequency Components in GANs Training. ACM Transactions on Multimedia Computing, Communications, and Applications, 2023. (CCF-B, IF: 5.2, 中科院 3 區, JCR Q1).
【3】 Yi Wu*, Ziqiang Li*, Chaoyue Wang, Heliang Zheng, Shanshan Zhao, Bin Li, and Dacheng Tao. Domain Re-Modulation for Few-Shot Generative Domain Adaptation. NeurIPS 2023 (CCF-A, 機器學習三大頂會).
- ~2022:
【1】Ziqiang Li, Chaoyue Wang, Heliang Zheng, Jing Zhang, and Bin Li. FakeCLR: Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANs. ECCV 2022 (CCF-B, 計算機視覺三大頂會).
【2】Ziqiang Li, Pengfei Xia, Rentuo Tao, Hongjing Niu, Bin Li. A New Perspective on Stabilizing GANs training: Direct Adversarial Training. IEEE Transactions on Emerging Topics in Computational Intelligence, 2022. (IF: 5.3, 中科院 2 區, JCR Q1).
【3】Ziqiang Li, Rentuo Tao, Jie Wang, Fu Li, Hongjing Niu, Mingdao Yue, Bin Li. Interpreting the Latent Space of GANs via Measuring Decoupling. IEEE Transaction on Artificial Intelligence, 2021.
【4】Pengfei Xia, Hongjing Niu, Ziqiang Li, Bin Li. Enhancing backdoor attacks with multi-level mmd regularization. IEEE Transaction on Dependable and Secure Computing, 2022. (CCF-A, IF: 7.3, 中科院 1 區, JCR Q1).
【5】Pengfei Xia, Ziqiang Li, Wei Zhang, Bin Li. Data-Efficient Backdoor Attacks. IJCAI 2022 (CCF-A).
【6】 Ziqiang Li, Rentuo Tao, Hongjing Niu, Mingdao Yue, Bin Li. Interpreting the Latent Space of GANs via Correlation Analysis for Controllable Concept Manipulation. ICPR 2020 (CCF-C).
【7】 Ziqiang Li, Rentuo Tao, Qianrun Wu, Bin Li. DA-RefineNet: Dual-inputs Attention RefineNet for Whole Slide Image Segmentation. ICPR 2020 (CCF-C).
科研項目
國家自然科學基金青年基金（C類），面向黑盒半監督學習的高效後門攻擊方法研究，2026.01-2028.12，在研，主持
江蘇省自然科學基金青年基金， 基於後門水印的無標註數據集著作權保護方法研究，2025.07-2028.06，在研，主持
江蘇省高校自然科學研究面上項目，面向跨模態預訓練的數據集著作權保護方法研究，2025.07-2027.06，在研，主持
科研獎勵
2025江蘇省網路空間安全學會 青年科技獎
2025江蘇省雙創博士
