Weizhao Jin

Ph.D. Candidate

University of Southern California

Biography

Hi! I am a Ph.D. candidate in Computer Science at University of Southern California. My research interests focus on privacy-preserving machine/federated learning, AI safety, applied homomorphic encryption, and differential privacy.

I have had the opportunity to contribute to advancing the security and privacy standards in ML during my time at AWS and TensorOpera AI, mentored by the amazing: Dr. Tancrède Lepoint, Dr. Aws Albarghouthi, Dr. Muhammad Naveed, Dr. Shahin Navardi, and Dr. Chaoyang He.

During my years in school, I was also privileged to work with Prof. Srivatsan Ravi, Prof. Carlee Joe-Wong, Prof. Yuan Tian, and Prof. Wenyuan Xu.

Interests

Security & Privacy
Privacy-Preserving Machine Learning
Differential Privacy
Networking & IoT

Education

Ph.D. Candidate in Computer Science

University of Southern California
MEng in Computer Engineering, 2020

University of Virginia
BEng in Electrical Engineering, 2018

Zhejiang University

Experience

AWS Privacy & Security Automation, Applied Scientist Intern, Amazon, May 2024 - Aug. 2024
AWS Privacy Engineering, Applied Scientist Intern, Amazon, May 2023 - April 2024 (extended)
Privacy-Preserving Federated Learning, ML Privacy Researcher, TensorOpera AI, Oct. 2022 - Mar. 2023
Buyer Risk Prevention, Applied Scientist Intern, Amazon, May 2022 - Aug. 2022
Networking & Cybersecurity Division, Graduate Research Assistant, USC-ISI, Aug. 2020 - Now
Security Lab, Student Research Assistant, UVa, Oct. 2018 - May 2020
USSLAB, Student Research Assistant, ZJU, Oct. 2017 - June 2018

Recent Publications

More Publications

Shanshan Han, Wenxuan Wu, Baturalp Buyukates, Weizhao Jin, Yuhang Yao, Qifan Zhang, Salman Avestimehr, Chaoyang He. Kick Bad Guys Out! Zero-Knowledge-Proof-Based Anomaly Detection in Federated Learning. preprint, 2024.

PDF

Shanshan Han, Baturalp Buyukates, Zijian Hu, Han Jin, Weizhao Jin, Lichao Sun, Xiaoyang Wang, Chulin Xie, Yuhang Yao, Kai Zhang, Qifan Zhang, Yuhui Zhang, Carlee Joe-Wong, Chaoyang He, Salman Avestimehr. FedMLSecurity: A Benchmark for Attacks and Defenses in Federated Learning and Federated LLMs. 2024 ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2024.

PDF

Weizhao Jin*, Yuhang Yao*, Shanshan Han, Carlee Joe-Wong, Srivatsan Ravi, Salman Avestimehr, Chaoyang He. FedML-HE: An Efficient Homomorphic-Encryption-Based Privacy-Preserving Federated Learning System. NeurIPS 2023 Federated Learning Workshop, 2023.

PDF

Yuhang Yao, Weizhao Jin, Srivatsan Ravi, Carlee Joe-Wong. FedGCN: Convergence-Communication Tradeoffs in Federated Training of Graph Convolutional Networks. Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS), 2023.

PDF

Weizhao Jin, Shahin Navardi, Gaoyuan Du, Daniel Cociorva, Hakan Brunzell, Xiaoyang Liu. Cross-Region Privacy-Preserving Federated Tabular Learning. AMLC, 2023.

PDF

Yixiang Yao, Weizhao Jin, Srivatsan Ravi. Labeling without Seeing? Blind Annotation for Privacy-Preserving Entity Resolution. preprint, 2023.

PDF

Weizhao Jin, Erik Kline, T. K. Satish Kumar, Lincoln Thurlow, Srivatsan Ravi. 𝑃3𝑉: Privacy-Preserving Path Validation System for Multi-Authority Sliced Networks. preprint, 2023.

PDF

Weizhao Jin, Bhaskar Krishnamachari, Muhammad Naveed, Srivatsan Ravi, Eduard Sanou, Kwame-Lante Wright. Secure Publish-Process-Subscribe System for Dispersed Computing. In 41st International Symposium on Reliable Distributed Systems (SRDS), 2022.

PDF

Weizhao Jin, Srivatsan Ravi, Erik Kline. Decentralized Privacy-Preserving Path Validation for Multi-Slicing-Authority 5G Networks. In IEEE Wireless Communications and Networking Conference (WCNC), 2022.

PDF

Weizhao Jin*, Xiaoyu Ji*, Ruiwen He, Zhou Zhuang, Wenyuan Xu, Yuan Tian. SMS Goes Nuclear: Fortifying SMS-Based MFA in Online Account Ecosystem. In Workshop on Data-Centric Dependability and Security (co-located with the IEEE/IFIP International Conference on Dependable Systems and Networks), 2021.

PDF