LOKI: Large-scale Data Reconstruction Attack against Federated Learning through Model Manipulation
Joshua C. Zhao, Atul Sharma, Ahmed Roushdy Elkord, Yahya H. Ezzeldin, Salman Avestimehr, Saurabh Bagchi
The 45th IEEE Symposium on Security and Privacy (S&P 2024)
Link | Video

Leak and Learn: An Attacker’s Cookbook to Train Using Leaked Data from Federated Learning
Joshua C. Zhao, Ahaan Dabholkar, Atul Sharma, Saurabh Bagchi
The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2024)
Link | Video

The Resource Problem of Using Linear Layer Leakage Attack in Federated Learning
Joshua C. Zhao, Ahmed Roushdy Elkordy, Atul Sharma, Yahya H. Ezzeldin, Salman Avestimehr, Saurabh Bagchi
The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023)
Link | Video

Federated Learning Privacy: Attacks, Defenses, Applications, and Policy Landscape - A Survey
Joshua C. Zhao, S. Bagchi, S. Avestimehr, K. Chan, S. Chaterji, D. Dimitriadis, J. Li, N. Li, A. Nourian, H. Roth
ACM Computer Surveys (CSUR 2025)
Link

FLAIR: Defense against Model Poisoning Attack in Federated Learning
Atul Sharma, Wei Chen, Joshua C. Zhao, Qiang Qiu, Saurabh Bagchi, and Somali Chaterji
The 18th ACM ASIA Conference on Computer and Communications Security (ACM AsiaCCS 2023)
Link

How to Learn Collaboratively – Federated Learning to Peer-to-Peer Learning and What’s at Stake
Atul Sharma, Joshua C. Zhao, Wei Chen, Qiang Qiu, Saurabh Bagchi, and Somali Chaterji
DSN-2023: Disruptive Ideans and New Interdisplinary Results (DSN Disrupt 2023)
Link

Thermal Management for FPGA Nodes in HPC Systems
Yingyi Luo, Joshua C. Zhao, Arnav Aggarwal, Seda Ogrenci-Memik, and Kazutomo Yoshii
ACM Transactions on Design Automation of Electronic Systems (TODAES 2020)
Link

Pre-prints / Under-submission

Separate Classes, Separate Features? Separate Class Adversarial Training Reconciles Robust and Non-robust Features.
Joshua C. Zhao, Ahaan Daholkar, Sauraubh Bagchi

Are Fast Methods Stable in Adversarially Robust Transfer Learning?
Joshua C. Zhao, Sauraubh Bagchi

SEEMSeg: Calibration of SEEM for Weakly Supervised Point Cloud Semantic Segmentation.
Kasra Derakhshandeh, Joshua C. Zhao, Somali Chaterji