Cong Fang

Most-cited papers

Exploring deep neural networks via layer-peeled model: Minority collapse in imbalanced training
Cong Fang, Hangfeng He, Qi Long, Weijie Su
2021Proceedings of the National Academy of Sciences of the United States of America240 citations Open access
Semantic Scholar
Decentralised, collaborative, and privacy-preserving machine learning for multi-hospital data
Cong Fang, Adam Dziedzic, Lin Zhang, Laura Oliva +4 more
2024EBioMedicine41 citations Open access
Semantic Scholar
Proof-of-Learning is Currently More Broken Than You Think
Cong Fang, Hengrui Jia, Anvith Thudi, Mohammad Yaghini +4 more
2022European Symposium on Security and Privacy28 citations Open access
Semantic Scholar
Secure Noise Sampling for Differentially Private Collaborative Learning
Olive Franzese, Cong Fang, R. Garg, Xiao Wang +3 more
2025IACR Cryptology ePrint Archive11 citations Open access
Semantic Scholar
Robust and Actively Secure Serverless Collaborative Learning
Olive Franzese, Adam Dziedzic, Christopher A. Choquette-Choo, M. Thomas +6 more
2023Neural Information Processing Systems8 citations
Semantic Scholar
On the Fundamental Limits of Formally (Dis)Proving Robustness in Proof-of-Learning
Cong Fang, Hengrui Jia, Anvith Thudi, Mohammad Yaghini +4 more
2022arXiv.org7 citations Open access
Semantic Scholar
Privacy-Preserving Federated Learning for Coverage Prediction
Cong Fang, Akram Bin Sediq, H. Sokun, Israfil Bahceci +2 more
2024IEEE International Symposium on Personal, Indoor and Mobile Radio Communications0 citations
Semantic Scholar

Most-cited papers

Exploring deep neural networks via layer-peeled model: Minority collapse in imbalanced training

Decentralised, collaborative, and privacy-preserving machine learning for multi-hospital data

Proof-of-Learning is Currently More Broken Than You Think

Secure Noise Sampling for Differentially Private Collaborative Learning

Robust and Actively Secure Serverless Collaborative Learning

On the Fundamental Limits of Formally (Dis)Proving Robustness in Proof-of-Learning

Privacy-Preserving Federated Learning for Coverage Prediction