His research focuses on data security and privacy in a broad spectrum of application domains, such as social network analysis, machine learning, and mobile cloud computing. Topics that he is currently working on include secure and verifiable computation, adversarial robustness of learning systems, game-theoretical modeling.
Hiring Multiple positions for Postdoc, Ph.D., RA and intern are available (RA -- HKD 17500/month, Postdoc -- at least HKD 30000/month). Do not hesitate to contact me (through email) if you are interested.
Our current research mainly focuses on two general directions: adversarial robustness of learning systems, and secure and verifiable computation.
Adversarial Robustness of Learning Systems
Secure and Verifiable Computation
Certified robustness of graph neural networks against structural attacks via edge smoothing.
Kai Zhou, Yunhui Long, Yan Xu, Bo Li, and Yevgeniy Vorobeychik. In submission, 2020
How to Hide one’s Relationships from Link prediction Algorithms.
Marcin Waniek, Kai Zhou, Yevgeniy Vorobeychik, Esteban Moro, Tomasz P Michalak, and Talal Rahwan Scientific Reports, 2019, Nature Publishing Group
IEEE TBDP-mod: Secure privilege-based multilevel organizational data-sharing in cloud computing. Ehab Zaghloul, Kai Zhou, and Jian Ren IEEE Transactions on Big Data, 2019
IEEE TIFSPassbio: Privacy-preserving user-centric biometric authentication. Kai Zhou, and Jian Ren IEEE Transactions on Information Forensics and Security, 2018
IEEE TSCCASO: Cost-Aware Secure Outsourcing of General Computational Problems. Kai Zhou, and Jian Ren IEEE Transactions on Services Computing, 2018
IEEE TKDEPrivacy characterization and quantification in data publishing. Mohamed H. Afifi Ibrahim, Kai Zhou, and Jian Ren IEEE Transactions on Knowledge and Data Engineering, 2018
IEEE TIFSExpSOS: secure and verifiable outsourcing of exponentiation operations for mobile cloud computing. Kai Zhou, M. H. Afifi, and Jian Ren IEEE Transactions on Information Forensics and Security 12, no. 11 (2017): 2518-2531
IEEE TIFSCDMA system design and capacity analysis under disguised jamming. Tianlong Song, Kai Zhou, and Tongtong Li IEEE Transactions on Information Forensics and Security 11, no. 11 (2016): 2487-2498
UAI'20Robust Collective Classification against Structural Attacks. Kai Zhou and Yevgeniy Vorobeychik the 36th Conference on Uncertainty in Artificial Intelligence (UAI), 2020
AAAI'20Computing Equilibria in Binary Networked Public Goods Games. Sixie Yu*, Kai Zhou*, P. Jeffrey Brantingham, and Yevgeniy Vorobeychik (* equal contribution) 34th AAAI Conference on Artificial Intelligence (AAAI), 2020
ICDM'19Adversarial Robustness of Similarity-Based Link Prediction. Kai Zhou, Tomasz P. Michalak , and Yevgeniy Vorobeychik 19th IEEE International Conference on Data Mining (ICDM), 2019 One of best papers of ICDM 2019
AAMAS'19Attacking Similarity-Based Link Prediction in Social Networks. Kai Zhou, Tomasz P. Michalak, Marcin Waniek, Talal Rahwan, and Yevgeniy Vorobeychik International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2019
Globecom'18Security and Privacy Enhancement for Outsourced Biometric Identification. Kai Zhou, and Jian Ren IEEE Global Communications Conference (GLOBECOM), 2018
ICCCN'16Secure fine-grained access control of mobile user data through untrusted cloud. Kai Zhou, and Jian Ren 25th International Conference on Computer Communication and Networks (ICCCN), 2016
ICC'16Secure outsourcing of scalar multiplication on elliptic curves. Kai Zhou, and Jian Ren IEEE International Conference on Communications (ICC), 2016
ICC'16LinSOS: Secure outsourcing of linear computations based on affine mapping. Kai Zhou, and Jian Ren IEEE International Conference on Communications (ICC), 2016
ICASSP'16Robust CDMA receiver design under disguised jamming. Kai Zhou, Tianlong Song, Jian Ren, and Tongtong Li IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2016
Security and efficiency trade-offs for cloud computing and storage. Jian Li, Kai Zhou, and Jian Ren IEEE Resilience Week (RWS), 2015