01
Trustworthy AI
Building transparent, reliable AI systems that are worthy of trust in high-impact settings.
Assistant Professor
Maranus
Huajie
Chen
Trustworthy AI · Biosecurity · Cybersecurity & Privacy
Research program
Technology people can trust.
My research focuses on Trustworthy AI, Biosecurity, Cybersecurity & Privacy to develop accountable systems that remain safe and useful in the real world.
02
Biosecurity
Examining how emerging technologies can be developed and deployed with biological risks in mind.
03
Cybersecurity & privacy
Advancing digital systems that safeguard security, privacy, and individual autonomy.
Academic service
Supporting the research community.
I contribute to the wider research community through peer review and by helping academic venues run thoughtful, engaging events.
01
Reviewer
Providing careful, constructive reviews for research venues in trustworthy AI, cybersecurity, privacy, and related areas.
- ACM CCSACM Conference on Computer and Communications Security
- USENIX SecUSENIX Security Symposium
- IEEE TIFSIEEE Transactions on Information Forensics and Security
- IEEE TDSCIEEE Transactions on Dependable and Secure Computing
- AAAIAssociation for the Advancement of Artificial Intelligence
- ACM MMACM International Conference on Multimedia
- CSURACM Computing Survey
- ACM TOPSACM Transactions on Privacy and Security
- NNNeural Networks
- PRPattern Recognition
- KBSKnowledge-Based Systems
- KSEMInternational Conference on Knowledge Science, Engineering and Management
- ICA3PPInternational Conference on Algorithms and Architectures for Parallel Processing
- WAICAThe World Artificial Intelligence Conference Academic
02
Host
Hosting academic sessions and events, helping speakers and participants exchange ideas clearly and productively.
- Program CommitteeThe 4th International Conference on Data Security and Privacy Protection (DSPP 2026)
- Program CommitteeThe First World Artificial Intelligence Conference Academic (WAICA 2026)
- Program CommitteeThe 41st Annual AAAI Conference on Artificial Intelligence (AAAI 2027)
- Program CommitteeThe 16th International Symposium on Cyberspace Safety and Security (CSS 2026)
- Local ChairThe 18th International Conference on Knowledge Science, Engineering and Management (KSEM 2025)
- Program CommitteeThe 24th International Conference on Algorithms and Architectures for Parallel Processing (ICA3PP 2024)
Selected publications
Recent work & collaborations.
2026
CSC: Turning the Adversary’s Poison Against Itself
Shi, Y., Guo, X., Chen, H.*, Zhu, T., Liu, B., & Zhou, W.
Australasian Conference on Information Security and Privacy, pp. 303–323. Singapore: Springer Nature Singapore
2026
A Backdoor-Assisted Inversion Framework for Model Abuse Verification
Sun, H., Zhu, T., Ge, X., Wang, D., Chen, H., Fang, B., & Zhou, W.
IEEE Transactions on Dependable and Secure Computing
2026
Bias-Corrected Momentum and Dynamic Step Bounding for Transferable Re-ID Attacks
Yang, H., Chen, H.*
The 16th International Symposium on Cyberspace Safety and Security
2025
Stand-in model protection: synthetic defense for membership inference and model inversion attacks
Chen, H., Zhu, T., Ji, S., & Zhou, W.
Knowledge-Based Systems, 316, 113339
2025
Queen: Query unlearning against model extraction
Chen, H., Zhu, T., Zhang, L., Liu, B., Wang, D., Zhou, W., & Xue, M.
IEEE Transactions on Information Forensics and Security
2024
When deep learning meets watermarking: A survey of application, attacks and defenses
Chen, H., Liu, C., Zhu, T., & Zhou, W.
Computer Standards & Interfaces, 89, 103830
2024
High-frequency matters: attack and defense for image-processing model watermarking
Chen, H., Zhu, T., Liu, C., Yu, S., & Zhou, W.
IEEE Transactions on Services Computing, 17(4), 1565–1579
2023
Making DeepFakes more spurious: evading deep face forgery detection via trace removal attack
Liu, C., Chen, H., Zhu, T., Zhang, J., & Zhou, W.
IEEE Transactions on Dependable and Secure Computing, 20(6), 5182–5196
2020
Privacy-preserving SVM on outsourced genomic data via secure multi-party computation
Chen, H., Ünal, A. B., Akgün, M., & Pfeifer, N.
Proceedings of the Sixth International Workshop on Security and Privacy Analytics, pp. 61–69
Academic path
Built across disciplines.
Assistant Professor
City University of Macau, Taipa, Macau SAR, China
Ph.D. Computer Science
University of Technology Sydney, Sydney, New South Wales, Australia
M.Sc., Bioinformatics
Universität Tübingen, Tübingen, Baden-Württemberg, Germany
B.Sc., Biotechnology
Sun Yat-sen University, Guangzhou, Guangdong, China
Research group
People behind the research.
A community of researchers and students working across trustworthy AI, biosecurity, cybersecurity, and privacy.
Current Members
Researchers currently working with the group.
Yuchen (Jason) Shi
B.Sc. in Computer Science, 2024--Present
Current
Trustworthy AI, Biosecurity
Hailin (Cynthia) Yang
B.Sc. in Computer Science, 2024--Present
Current
Trustworthy AI
Yilin (Coco) Yang
B.Sc. in Computer Science, 2024--Present
Current
Trustworthy AI
Guangkai (Kevin) Jiang
B.Sc. in Computer Science, 2025--Present
Current
Trustworthy AI
Xin (Samuel) Guo
B.Sc. in Computer Science, 2025--Present
Current
Trustworthy AI, Biosecurity
Yang Yu
M.Sc. in Computer Science, 2025--Present
Current
Biosecurity, Cybersecurity & Privacy
Saibo (Allen) Ye
B.Sc. in Computer Science, 2025--Present
Current
Trustworthy AI, Cybersecurity & Privacy
Qianyu (Queeny) Chen
B.Sc. in Computer Science, 2025--Present
Current
Trustworthy AI
Alumni
Former students and where their work has taken them.
Sihui Wu
M.Sc. in Computer Science, 2024--2026
Now
National Civil Servant
Collaborate
Interested in the same questions?
I welcome conversations with researchers, students, and teams advancing trustworthy AI, biosecurity, cybersecurity, and privacy.