英国·威廉希尔(WilliamHill)中文官网-Official Website

您当前所在的位置：首页 > 师资队伍 > 教师名录

师资队伍

人才招聘

教师名录

胡宏盛

长聘教轨副教授

邮箱：hongsheng.hu@sjtu.edu.cn

所在研究所：信息安全与密码学研究所

个人简介

Dr. Hongsheng Hu is an Associate Professor in the School of Computer Science at Shanghai Jiao Tong University. From 2024 to 2026, he was a Lecturer in the School of Information and Physical Sciences at the University of Newcastle, Australia. Prior to that, he was a Postdoctoral Research Fellow at CSIRO’s Data61. He received his Ph.D. from the University of Auckland, New Zealand, under the supervision of Professor Xuyun Zhang, Professor Gillian Dobbie (Fellow of the Royal Society of New Zealand), and Professor Zoran Salcic (Fellow of the Royal Society of New Zealand).

His research focuses on trustworthy machine learning, with particular emphasis on privacy and security. His work investigates critical privacy vulnerabilities in machine learning systems and develops effective defense and mitigation strategies. His research has appeared in leading information security, artificial intelligence, and data mining venues, including IEEE S&P, NDSS, USENIX Security, NeurIPS, CVPR, ICLR, IJCAI, AAAI, The Web Conference (WWW), ICDM, ACM Computing Surveys, IEEE TDSC, and IEEE TIFS.

He regularly serves on the program committees of major international conferences, including ACM CCS, USENIX Security, NDSS AE, SaTML, ICLR, IJCAI, AAAI, and The Web Conference. He is an Associate Editor of IEEE Transactions on Information Forensics and Security and IEEE Transactions on Dependable and Secure Computing.

工作履历

2026-Now, Associate Professor, School of Computer Science, Shanghai Jiao Tong University
2024-2026, Lecturer, School of Computer and Information Sciences, University of Newcastle, Australia
2022-2024, Research Fellow, CSIRO's Data61, Australia
2018-2022, PhD, University of Auckland, New Zealand

论文发表

I have published 40+ papers in top information security, artificial intelligence, and data mining conferences. * indicates the work for which I am the lead author, including the first author, the (co-)corresponding author, or the first author being my student. The selected papers are listed as follows:

2026:

1. [IEEE S&P] Feiyue Xu, Hongsheng Hu*, Chaoxiang He, Sheng Hang, Hanqing Hu, Xiuming Liu, Yubo Zhao, Zhengyan Zhou, Bin Benjamin Zhu, Shi-Feng Sun, Dawu Gu, Shuo Wang. In IEEE Symposium on Security and Privacy (Oakland), 2026. [CCF A, BIG 4]

2. [NDSS] Ruixuan Liu, Toan Tran, Tianhao Wang, \textbf{Hongsheng Hu}, Shuo Wang, Li Xiong. ExpShield: Safeguarding Web Text from Unauthorized Crawling and Language Modeling Exploitation. In Network and Distributed System Security Symposium (NDSS) 2026. [CCF A, BIG 4]

3. [USENIX Security] Na Li, Yansong Gao, Hongsheng Hu, Boyu Kuang, Anmin Fu. CompLeak: Deep Learning Model Compression Exacerbates Privacy Leakage. In USENIX Security 2026. [CCF A, BIG 4, Distinguished Artifact Awards]

4. [ICLR] Di Zhao, Jingfeng Zhang, Hongsheng Hu, Philippe Fournier-Viger, Gillian Dobbie, Yun Sing Koh. Unlearning during training: Domain-specific gradient ascent for domain generalization. In The Fourteenth International Conference on Learning Representations (ICLR), 2026. [CCF A]

5. [AAAI] Xiaoxiao Chi, Xuyun Zhang, Yan Wang, Hongsheng Hu, Wanchun Dou. Reference Recommendation based Membership Inference Attack against Hybrid-based Recommender Systems. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2026. [CCF A]

学术服务

TPC Member:

USENIX Security Symposium 2027
IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) 2027
ACM SIGSAC Conference on Computer and Communications Security (CCS) 2026
Network and Distributed System Security (NDSS) Symposium AE, 2024, 2025, 2026
International Symposium on Research in Attacks, Intrusions and Defenses (RAID), 2025, 2026
AAAI Conference on Artificial Intelligence 2024, 2025, 2026
ACM International Conference on Web Search and Data Mining (WSDM) 2026, Senior PC

Editor:

Associate Editor, IEEE Transactions on Information Forensics and Security (TIFS), CCF-A, 2025-Now
Associate Editor, IEEE Transactions on Dependable and Secure Computing (TDSC), CCF-A, 2025-Now