3 papers
cs.LG2026
Revisiting ML Training under Fully Homomorphic Encryption: Convergence Guarantees, Differential Privacy, and Efficient Algorithms
Yvonne Zhou, Mingyu Liang, Ivan Brugere +5
We present the first theoretical convergence analysis of machine learning training under fully homomorphic encryption (FHE), combined with a differentially private (DP) training al…
cs.CR2026
AgentCrypt: Advancing Privacy and (Secure) Computation in AI Agent Collaboration
Harish Karthikeyan, Yue Guo, Leo de Castro +5
As AI agents increasingly operate in complex environments, ensuring reliable, context-aware privacy is critical for regulatory compliance. Traditional access controls are insuffici…
cs.CR2025
Armadillo: Robust Single-Server Secure Aggregation for Federated Learning with Input Validation
Yiping Ma, Yue Guo, Harish Karthikeyan +1
This paper presents a secure aggregation system Armadillo that has disruptive resistance against adversarial clients, such that any coalition of malicious clients (within the toler…