About Me
I am an Applied Scientist at Amazon Web Services, working on Security and AI research. I earned my Ph.D. in Computer Science at UC San Diego, co-advised by Prof. Rajesh K. Gupta and Prof. Jingbo Shang. Prior to UCSD, I received my B.S. in Computer Science at Fudan University.
My current research focuses on reliable AI systems for cybersecurity that can reason, adapt, and act in adversarial environments. My work includes threat detection, structured threat intelligence extraction, and red-teaming. I develop post-training methods and agentic systems that analyze complex security contexts, reason about risks and adversary behaviors, and validate security hypotheses through executable evaluation.
Another line of my work studies robust AI for edge and distributed systems. This includes federated learning under data and system heterogeneity, and learning from limited or weakly supervised data.
Selected Publications
-
QED: An Open-Source Multi-Agent System for Generating Mathematical Proofs on Open Problems.
Chenyang An, Qihao Ye, Minghao Pan, Jiayun Zhang.
arXiv preprint arXiv:2604.24021
-
Taming Update Drift in Asynchronous Federated Learning via Orthogonal Calibration.
Jiayun Zhang, Shuheng Li, Haiyu Huang, Xiaofan Yu, Chenyang An, Rajesh K. Gupta, Jingbo Shang.
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2026.
-
Multi-Domain Marker Aggregation for Threat Detection in Cloud Environments.
Junshen Xu, Jiayun Zhang, Yi Fan.
The Web Conference (WWW), 2026. Selected as oral.
-
Matching Skeleton-based Activity Representations with Heterogeneous Signals for HAR.
Shuheng Li, Jiayun Zhang, Xiaohan Fu, Xiyuan Zhang, Jingbo Shang, Rajesh K. Gupta.
ACM Conference on Embedded Networked Sensor Systems (SenSys), 2025.
-
REACT: Residual-Adaptive Contextual Tuning for Fast Model Adaptation in Threat Detection.
Jiayun Zhang, Junshen Xu, Bugra Can, Yi Fan.
The Web Conference (WWW), 2025.
Also presented at Workshop on Fine-Tuning in Modern Machine Learning: Principles and Scalability at NeurIPS, 2024.
-
Contextual Inference From Sparse Shopping Transactions Based on Motif Patterns.
Jiayun Zhang, Xinyang Zhang, Dezhi Hong, Rajesh K. Gupta, and Jingbo Shang.
IEEE Transactions on Knowledge and Data Engineering (TKDE), 2025.
-
Learn from Failure: Fine-tuning LLMs with Trial-and-Error Data for Intuitionistic Propositional Logic Proving
Chenyang An, Zhibo Chen, Qihao Ye, Emily First, Letian Peng, Jiayun Zhang, Zihan Wang, Sorin Lerner, Jingbo Shang.
Annual Meeting of the Association for Computational Linguistics (ACL), 2024.
-
How Few Davids Improve One Goliath: Federated Learning in Resource-Skewed Edge Computing Environments.
Jiayun Zhang, Shuheng Li, Haiyu Huang, Zihan Wang, Xiaohan Fu, Dezhi Hong, Rajesh K. Gupta, Jingbo Shang.
The Web Conference (WWW), 2024. Selected as oral.
-
Physics-Informed Data Denoising for Real-Life Sensing Systems.
Xiyuan Zhang, Xiaohan Fu, Diyan Teng, Chengyu Dong, Keerthivasan Vijayakumar, Jiayun Zhang, Ranak Roy Chowdhury, Junsheng Han, Dezhi Hong, Rashmi Kulkarni, Jingbo Shang and Rajesh K. Gupta.
ACM Conference on Embedded Networked Sensor Systems (SenSys), 2023.
-
Unleashing the Power of Shared Label Structures for Human Activity Recognition.
Xiyuan Zhang, Ranak Roy Chowdhury, Jiayun Zhang, Dezhi Hong, Rajesh K. Gupta, Jingbo Shang.
ACM International Conference on Information and Knowledge Management (CIKM), 2023.
-
Navigating Alignment for Non-identical Client Class Sets: A Label Name-Anchored Federated Learning Framework.
Jiayun Zhang, Xiyuan Zhang, Xinyang Zhang, Dezhi Hong, Rajesh K. Gupta, Jingbo Shang.
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2023.
-
Minimally Supervised Contextual Inference from Human Mobility: An Iterative Collaborative Distillation Framework.
Jiayun Zhang, Xinyang Zhang, Dezhi Hong, Rajesh K. Gupta, and Jingbo Shang.
International Joint Conferences on Artificial Intelligence (IJCAI), 2023.
-
Blacklight: Scalable Defense for Neural Networks against Query-Based Black-Box Attacks.
Huiying Li, Shawn Shan, Emily Wenger, Jiayun Zhang, Haitao Zheng, Ben Y. Zhao.
USENIX Security Symposium, 2022.
-
Fawkes: Protecting Privacy against Unauthorized Deep Learning Models.
Shawn Shan, Emily Wenger, Jiayun Zhang, Huiying Li, Haitao Zheng, Ben Y. Zhao.
USENIX Security Symposium, 2020.
-
Detecting Malicious Accounts in Online Developer Communities Using Deep Learning.
Qingyuan Gong, Jiayun Zhang, Yang Chen, Qi Li, Yu Xiao, Xin Wang, Pan Hui.
ACM International Conference on Information and Knowledge Management (CIKM), 2019.
Work Experience
-
Amazon Web Service
Applied Scientist in Security Analytics and AI Research (SAAR) Team. May 2025 – Present
Professional Services
- Conference Program Committee Member / Reviewer: KDD'26/25/23, WWW'25/24, SDM'24, AAAI'24/23, UbiComp'23.
- Journal Reviewer: Computer Communications, IEEE Internet of Things Journal.