|
-
人工智能安全、隐私保护、多媒体安全
- Shixin Li, Zewei Li, Xiaojing Ma*, Xiaofan Bai, Pingyi Hu, Dongmei Zhang, and Bin Benjamin Zhu. Consensus-Robust Transfer Attacks via Parameter and Representation Perturbations. In proceedings of the Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS), San Diego, USA, December 2-December 7, 2025: 1-19..
- Chaoxiang He, Yimiao Zeng, Xiaojing Ma*, Bin Benjamin Zhu, Zewei Li, Shixin Li, and Hai Jin. Mysticmask: Adversarial mask for impersonation attack against face recognition systems. In proceedings of 2024 IEEE International Conference on Multimedia and Expo (ICME). Niagara Falls, Canada, July 15-July19, 2024: 1-6..
- Shixin Li, Chaoxiang He, Xiaojing Ma, Bin Benjamin Zhu, Shuo Wang, Hongsheng Hu, Dongmei Zhang, and Linchen Yu. Enhancing Adversarial Transferability with Checkpoints of a Single Model's Training. In Proceedings of 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2025), Nashville, TN, USA, June 11-June 15, 2025: 20685-20694..
- Chaoxiange He, Xiaojing Ma*, Bin B. Zhu, Yimiao Zeng, Hanqing Hu, Xiaofan Bai, Hai Jin and Dongmei Zhang. DorPatch: Distributed and Occlusion-Robust Adversarial Patch to Evade Certifiable Defenses. In Proceedings of 2024 Network and Distributed System Security Symposium (NDSS 2024), February 26–March 1, San Diego, California, USA, 2024:1-17..
- Pingyi Hu, Xiaofan Bai, Xiaojing Ma*, Chaoxiang He*, Dongmei Zhang, and Bin Benjamin Zhu. 2025. RESF: Regularized-Entropy-Sensitive Fingerprinting for Black-Box Tamper Detection of Large Language Models. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, Suzhou, China, November 4-November 9, 2025:1-10. .
- Chaoxiang He, Xiaofan Bai, Xiaojing Ma*, Bin B. Zhu, Pingyi Hu, Jiayun Fu, Hai Jin, and Dongmei Zhang. 2024. Towards stricter black-box integrity verifications. In Proceedings of the 32nd ACM International Conference on Multimedia(MM 2024), Melbourne, Australia, October 28-November 1, 2024:9875–9884. .
- 1、 一种JPEG兼容的隐写分析方法与系统，马晓静，金海，刘姣姣，ZL201410195302.9.2020/09/29
- 2、 一种应用于监控视频隐私保护的压缩域失真漂移补偿方法，马晓静，金海，霍海峰， ZL201310750839.2 .2020/09/29
- 3、 基于同态加密的 JPEG 图像密文下解压缩方法及系统，金海，马晓静，汤媛媛， 201810890668.6 .2020/09/29
- 4、 一种HEVC/H.265视频加密方法和视频密文运动检测方法，金海，马晓静，彭欢， 201711314499.3 .2020/09/29
- 5、 一种隐私保护下的视频运动物体轨迹跟踪方法及系统，金海，马晓静，曹思行， 201711184418.2.2020/09/29
- 暂无内容