姓名：石震波
电子邮箱：zbshi@ustc.edu.cn
个人主页：https://shizhenbo.github.io/
地址：中国科学技术大学西区科技实验楼西楼1405
主要研究方向：人工智能安全、计算机视觉、AI for Science
个人简介：
石震波，博士，现任中国科学技术大学计算机科学与技术学院特任副研究员，硕士生导师。主要研究方向为人工智能安全、计算机视觉和AI for Science。主持省部级自然科学基金等项目，同时参与科技创新2030重大项目。主持的创新计划项目曾获评优秀奖。近五年来，在TDSC/ICCV/AAAI/ACM MM/IJCAI等国际会议/期刊上共发表CCF A/B类论文数十篇。担任NeurIPS/ICML/CVPR/AAAI/ICCV/ACM MM/ICLR/ECCV等多个国际顶级会议的审稿人。
招生信息：欢迎兼具思辨能力与实践动手能力，且对人工智能领域抱有浓厚研究兴趣的同学与我联系。
主持和参与的项目：
1. 面向多模态模型的跨域攻击与鲁棒防御研究，江苏省自然科学基金青年项目，主持
2. 面向AI多模态模型的高效攻击与鲁棒防御研究，MEAC国重实验室项目，主持
3. 自动驾驶系统网络安全关键技术研究与应用，安徽省科技重大专项项目，参与
4. 基于Wi-Fi的人体动作智能感知关键技术研究，国家自然科学基金面上项目，参与
所获奖项和荣誉：
1. 墨子杰出青年特资津贴
2. 小米青年学者
3. 金砖国家青年科学家代表
4. 首届网空协会创新资助计划优秀项目奖
代表性著作：
[1]. Zhenbo Shi, Zhidong Yu, Yuxuan Zhang, Wei Yang*, Liusheng Huang. A Unified Perspective from Diffuse Deviation to Target Hijacking. IEEE Transactions on Dependable and Secure Computing. (CCF A类)
[2]. Yuxuan Zhang, Zhenbo Shi*, Shuchang Wang, Wei Yang*, Shaowei Wang, Yinxing Xue. RP-PGD: Boosting Segmentation Robustness with a Region-and-Prototype Based Adversarial Attack. in 2025 Proceedings of the AAAI Conference on Artificial Intelligence. (CCF A类)
[3]. Zhenbo Shi, Xiaoman Liu, Yuxuan Zhang, Shuchang Wang, Rui Shu, Zhidong Yu*, Wei Yang*, Liusheng Huang. Stop Diverse OOD Attacks: Knowledge Ensemble for Reliable Defense. in 2025 Proceedings of the AAAI Conference on Artificial Intelligence. (CCF A类)
[4]. Zhenbo Shi, Wei Yang*, Zhenbo Xu, Zhidong Yu, Liusheng Huang. Reinforcement Learning-based Adversarial Attacks on Object Detectors using Reward Shaping. in 2023 Proceedings of the 31th ACM International Conference on Multimedia. (CCF A类)
[5]. Zhidong Yu, Xiaoman Liu, Jiajun Hu, Zhenbo Shi*, Wei Yang*. AAKR: Adversarial Attack-based Knowledge Retention for Continual Semantic Segmentation. in 2025 Proceedings of the AAAI Conference on Artificial Intelligence. (CCF A类)
[6]. Yuxuan Zhang, Zhenbo Shi, Wei Yang*, Shuchang Wang, Shaowei Wang, Yinxing Xue*. GenSeg: On Generating Unified Adversary for Segmentation. in 2024 Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence. (CCF A类)
[7]. Zhenbo Xu, Ajin Meng, Zhenbo Shi, Wei Yang*, Zhi Chen, Liusheng Huang. Continuous Copy-Paste for One-stage Multi-object Tracking and Segmentation. Proceedings of the IEEE/CVF International Conference on Computer Vision. (CCF A类)
[8]. Zhenbo Shi, Zhi Chen, Zhenbo Xu, Wei Yang*, Zhidong Yu, Liusheng Huang. Shape Prior Guided Attack: Sparser Perturbations on 3D Point Clouds. in 2022 Proceedings of the AAAI Conference on Artificial Intelligence. (CCF A类)
[9]. Zhenbo Shi, Zhi Chen, Zhenbo Xu, Wei Yang*, Liusheng Huang. AtHom: Two Divergent Attentions Stimulated By Homomorphic Training in Text-to-Image Synthesis. in 2022 Proceedings of the 30th ACM International Conference on Multimedia. (CCF A类)
[10]. Zhidong Yu, Zhenbo Shi*, Xiaoman Liu, Wei Yang*. “PFFAA: Prototype-based Feature and Frequency Alteration Attack for Semantic Segmentation”. in 2024 Proceedings of the 32nd ACM International Conference on Multimedia. (CCF A类)
（更新于2025年6月）