Ka-Ho Chow (周嘉豪)
Assistant Professor
Department of Computer Science
School of Computing and Data Science
The University of Hong Kong (HKU)
Email: kachow@cs.hku.hk
Office: CB-403, Chow Yei Ching Building, Pok Fu Lam Rd, Hong Kong
News
- Dec 2024 A preprint on RAG is released on arXiv
- Nov 2024 A preprint on VLM for gradient inversion attacks is released on arXiv
- Nov 2024 A preprint on multi-target backdoor attacks is released on arXiv
- Oct 2024 A preprint on intellectual property protection in FL is released on arXiv
- Aug 2024 One paper on robust GNN against backdoor attacks accepted by AISec 2024
- Jul 2024 A preprint on genomic data privacy is released on bioRxiv
- Jul 2024 One paper on personalized privacy protection against unauthorized face recognition accepted by ECCV 2024
- Jun 2024 Honored to receive funding from the RGC Early Career Scheme to investigate a new backdoor threat in federated learning
- May 2024 Honored to receive funding from the Croucher Foundation to make distributed machine learning accountable
- May 2024 One paper on privacy protection against unauthorized face recognition accepted by PETS 2024
- May 2024 One demo paper on data poisoning in federated learning accepted by ICDCS 2024
- Apr 2024 One paper on LLM for backdoor attacks accepted by IJCAI 2024
- Apr 2024 One paper on efficient privacy attacks in federated learning accepted by CVPRW 2024
- Apr 2024 A preprint on robust few-shot learning is released on arXiv
- Feb 2024 A survey on privacy threats in vertical federated learning is released on arXiv
- Jan 2024 One paper on LLM for blockchain security accepted by WWW 2024 [More]
Ka-Ho Chow (周嘉豪)
The University of Hong KongI am an Assistant Professor in the Department of Computer Science, School of Computing and Data Science at the University of Hong Kong (HKU). I was named an IBM PhD Fellow in 2022 and a Croucher Scholar in 2021. Before joining HKU, I was a research scientist at IBM Research and received my Ph.D. in Computer Science from the Georgia Institute of Technology (Georgia Tech), advised by Prof. Ling Liu.
My research interests are at the intersection of machine learning, cybersecurity, and systems. The overarching goal is to amplify the real-world impact of artificial intelligence by building trustworthy technologies through an adversarial lens. To this end, my recent work focuses on (i) understanding new security and privacy threats to AI systems and (ii) developing attack-resilient solutions through algorithmic and infrastructure optimization. These efforts span various learning approaches, including centralized and federated learning, and cover a range of applications across, e.g., large language models and visual recognition.
Recruitment: I have several openings for Ph.D. students, postdoctoral researchers, research assistants, and interns. If you are interested in machine learning, cybersecurity, and systems, please reach out to me via email: kachow@cs.hku.hk
Research Interests
Trustworthy AI Systems; Cybersecurity; ML for Systems & Systems for ML
Selected Publications
[Google Scholar]- AISec 2024 Yuxuan Zhu, Michael Mandulak, Kerui Wu, George Slota, Yuseok Jeon, Ka-Ho Chow, and Lei Yu, "On the Robustness of Graph Reduction Against GNN Backdoor," ACM Workshop on Artificial Intelligence and Security (AISec), Oct 18, 2024. [PDF]
- ECCV 2024 Ka-Ho Chow, Sihao Hu, Tiansheng Huang, and Ling Liu, "Personalized Privacy Protection Mask Against Unauthorized Facial Recognition," European Conference on Computer Vision (ECCV), Milan, Italy, Sep. 29-Oct. 4, 2024. [PDF] [CODE]
- IJCAI 2024 Ka-Ho Chow, Wenqi Wei, and Lei Yu, "Imperio: Language-Guided Backdoor Attacks for Arbitrary Model Control," International Joint Conference on Artificial Intelligence (IJCAI), Jeju, South Korea, Aug. 3-9, 2024. [PDF] [CODE]
- CVPRW 2024 Nawrin Tabassum, Ka-Ho Chow, Xuyu Wang, Wenbin Zhang, and Yanzhao Wu, "On the Efficiency of Privacy Attacks in Federated Learning," IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops - FedVision (CVPRW), Seattle, WA, USA, Jun. 17-21, 2024. [PDF] [CODE]
- WWW 2024 Sihao Hu, Tiansheng Huang, Ka-Ho Chow, Wenqi Wei, Yanzhao Wu, and Ling Liu, "ZipZap: Efficient Training of Language Models for Ethereum Fraud Detection," The Web Conference (WWW), Singapore, May 13-17, 2024. [PDF] [CODE]
- EuroSys 2024 Ka-Ho Chow, Umesh Deshpande, Veera Deenadhayalan, Sangeetha Seshadri, and Ling Liu, "Atlas: Hybrid Cloud Migration Advisor for Interactive Microservices," ACM European Conference on Computer Systems (EuroSys), Athens, Greece, Apr. 22-25, 2024. [PDF] [CODE]
- WACV 2024 Fatih Ilhan, Ka-Ho Chow, Sihao Hu, Tiansheng Huang, Selim Furkan Tekin, Wenqi Wei, Yanzhao Wu, Myungjin Lee, Ramana Kompella, Hugo Latapie, Gaowen Liu, and Ling Liu, "Adaptive Deep Neural Network Inference Optimization with EENet," IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA, Jan 4-8, 2024. [PDF] [CODE]
- NeurIPS 2023 Tiansheng Huang, Sihao Hu, Ka-Ho Chow, Fatih Ilhan, Selim Furkan Tekin, and Ling Liu, "Lockdown: Backdoor Defense for Federated Learning with Isolated Subspace Training," Neural Information Processing Systems (NeurIPS), New Orleans, LA, USA, Dec 10-16, 2023. [PDF] [CODE]
- ICDM 2023 Wenqi Wei, Ka-Ho Chow, Fatih Ilhan, Yanzhao Wu, and Ling Liu, "Model Cloaking against Gradient Leakage," IEEE International Conference on Data Mining (ICDM), Shanghai, China, Dec 1-4, 2023. [PDF] [CODE]
- ICDM 2023 Yanzhao Wu, Ka-Ho Chow, Wenqi Wei, and Ling Liu, "Exploring Model Learning Heterogeneity for Boosting Ensemble Robustness," IEEE International Conference on Data Mining (ICDM), Shanghai, China, Dec 1-4, 2023. [PDF] [CODE]
- CVPR 2023 Ka-Ho Chow, Ling Liu, Wenqi Wei, Fatih Ilhan, and Yanzhao Wu, "STDLens: Model Hijacking-Resilient Federated Learning for Object Detection," IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, Canada, Jun. 18-22, 2023. [PDF]
- ICDM 2022 Ka-Ho Chow and Ling Liu, "Boosting Object Detection Ensembles with Error Diversity," IEEE International Conference on Data Mining (ICDM), Orlando, FL, USA, Nov. 28 - Dec. 1, 2022. [PDF] [CODE]
- EuroSys 2022 Ka-Ho Chow, Umesh Deshpande, Sangeetha Seshadri, and Ling Liu, "DeepRest: Deep Resource Estimation for Interactive Microservices," ACM European Conference on Computer Systems (EuroSys), Rennes, France, Apr. 5-8, 2022. [PDF] [CODE]
- SIGKDD 2021 Ka-Ho Chow and Ling Liu, "Robust Object Detection Fusion Against Deception," ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (SIGKDD), Singapore, Aug. 14-18, 2021. [PDF] [CODE]
- SIGMOD 2021 Ka-Ho Chow, Umesh Deshpande, Sangeetha Seshadri, and Ling Liu, "SRA: Smart Recovery Advisor for Cyber Attacks," ACM SIGMOD International Conference on Management of Data (SIGMOD), Xi'an, Shaanxi, China, Jun. 20-25, 2021. [PDF] 🎮 Demo
- CVPR 2021 Yanzhao Wu, Ling Liu, Zhongwei Xie, Ka-Ho Chow, and Wenqi Wei, "Boosting Ensemble Accuracy by Revisiting Ensemble Diversity Metrics," IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, Jun. 19-25, 2021. [PDF] [CODE]
- TPS-ISA 2020 Ka-Ho Chow, Ling Liu, Margaret Loper, Juhyun Bae, Mehmet Emre Gursoy, Stacey Truex, Wenqi Wei, and Yanzhao Wu, "Adversarial Objectness Gradient Attacks on Real-time Object Detection Systems," IEEE International Conference on Trust, Privacy and Security in Intelligent Systems, and Applications (TPS-ISA), Atlanta, GA, USA, Dec. 1-3, 2020. [PDF] [CODE] 🎮 Demo
- ESORICS 2020 Ka-Ho Chow, Ling Liu, Mehmet Emre Gursoy, Stacey Truex, Wenqi Wei, and Yanzhao Wu, "Understanding Object Detection Through An Adversarial Lens," European Symposium on Research in Computer Security (ESORICS), Guildford, United Kingdom, Sep. 14-18, 2020. [PDF] [CODE]
- ESORICS 2020 Wenqi Wei, Ling Liu, Margaret Loper, Ka-Ho Chow, Mehmet Emre Gursoy, Stacey Truex, and Yanzhao Wu, "A Framework for Evaluating Gradient Leakage Attacks in Federated Learning," European Symposium on Research in Computer Security (ESORICS), Guildford, United Kingdom, Sep. 14-18, 2020. [PDF] [CODE] 🎮 Demo
- EdgeSys 2020 Stacey Truex, Ling Liu, Ka-Ho Chow, Mehmet Emre Gursoy, and Wenqi Wei, "LDP-Fed: Federated Learning with Local Differential Privacy," ACM International Workshop on Edge Systems, Analytics and Networking (EdgeSys), Heraklion, Crete, Greece, Apr. 27, 2020. [PDF] [CODE] 🏆 Best Paper Award
- BigData 2019 Ka-Ho Chow, Wenqi Wei, Yanzhao Wu, and Ling Liu, "Denoising and Verification Cross-Layer Ensemble Against Black-box Adversarial Attacks," IEEE International Conference on Big Data (BigData), Los Angeles, CA, USA, Dec. 9-12, 2019. [PDF]
- TSC Wenqi Wei, Ka-Ho Chow, Yanzhao Wu, and Ling Liu, "Demystifying Data Poisoning Attacks in Distributed Learning as a Service," IEEE Transactions on Services Computing (TSC), Vol. 17, No. 1, pp. 237-250, February 2024.
- TIST Yanzhao Wu, Ka-Ho Chow, Wenqi Wei, and Ling Liu, "Hierarchical Pruning of Deep Ensembles with Focal Diversity," ACM Transactions on Intelligent Systems and Technology (TIST), Vol. 15, No. 15, pp. 1-24, January 2024. [PDF] [CODE]
- TPDS Wenqi Wei, Ling Liu, Jingya Zhou, Ka-Ho Chow, and Yanzhao Wu, "Securing Distributed SGD against Gradient Leakage Threats," IEEE Transactions on Parallel and Distributed Systems (TPDS), Vol. 34, No. 7, pp. 2040-2054, July 2023. [PDF] [CODE]
- TIFS Mehmet Emre Gursoy, Ling Liu, Ka-Ho Chow, Stacey Truex, and Wenqi Wei, "An Adversarial Approach to Protocol Analysis and Selection in Local Differential Privacy," IEEE Transactions on Information Forensics and Security (TIFS), Vol. 17, pp. 1785-1799, May 2022. [PDF]
- PREPRINT Junyuan Zhang, Qintong Zhang, Bin Wang, Linke Ouyang, Zichen Wen, Ying Li, Ka-Ho Chow, Conghui He, and Wentao Zhang, "OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation," arXiv preprint arXiv:2412.02592, Dec 3, 2024. [PDF] [CODE]
- PREPRINT Junjie Shan, Ziqi Zhao, Jialin Lu, Rui Zhang, Siu Ming Yiu, and Ka-Ho Chow, "Geminio: Language-Guided Gradient Inversion Attacks in Federated Learning," arXiv preprint arXiv:2411.14937, Nov 22, 2024. [PDF] [CODE]
- PREPRINT Jialin Lu, Junjie Shan, Ziqi Zhao, and Ka-Ho Chow, "AnywhereDoor: Multi-Target Backdoor Attacks on Object Detection," arXiv preprint arXiv:2411.14243, Nov 21, 2024. [PDF] [CODE]
- PREPRINT Kaijing Luo and Ka-Ho Chow, "Unharmful Backdoor-based Client-side Watermarking in Federated Learning," arXiv preprint arXiv:2410.21179, Oct 29, 2024. [PDF] [CODE]
- PREPRINT Jingcheng Zhang, Yingxuan Ren, Man Ho Au, Ka-Ho Chow, Yekai Zhou, Lei Chen, Yanmin Zhao, Junhao Su, and Ruibang Luo, "Towards a new standard in genomic data privacy: a realization of owner-governance," bioRxiv 2024.07.23.604393, Jul 24, 2024. [PDF] [CODE]
- PREPRINT Lei Yu, Meng Han, Yiming Li, Changting Lin, Yao Zhang, Mingyang Zhang, Yan Liu, Haiqin Weng, Yuseok Jeon, Ka-Ho Chow, and Stacy Patterson, "A Survey of Privacy Threats and Defense in Vertical Federated Learning: From Model Life Cycle Perspective," arXiv preprint arXiv:2402.03688, Feb 6, 2024. [PDF]
Lab Members
- Junjie Shan, Ph.D. Student, 2024/9-
- Ziqi Zhao, Ph.D. Student, 2024/10-
- Jialin Lu, Summer Intern, 2024
- Ruitong Liu, Summer Intern, 2024
Research Grants
- Principal Investigator, "Arbitrary-Control Backdoor Threats in Federated Learning: Attacks and Defenses," Hong Kong RGC Early Career Scheme (HKD 933,988), 2025 - 2028.
- Principal Investigator, "Trustworthy Federated Learning Against Model Leakage," Croucher Foundation Start-up (HKD 500,000), 2024 - 2029.
Teaching
- [FITE 1010] Introduction to Financial Technologies: Fall 2024
Selected Awards
- IBM PhD Fellowship, 2022
- Croucher Scholarship, Croucher Foundation, Hong Kong, 2021
- Best Paper Award, ACM International Workshop on Edge Systems, Analytics and Networking, 2020
- Chair's Fellowship, School of Computer Science, Georgia Tech, 2019
- Chan Tseng-Hsi Scholarship, Chan Tseng-Hsi Foundation, Hong Kong, 2013-2014
- Sir Edward Youde Memorial Prize, Hong Kong, 2009-2010