Antigoni Polychroniadou
3 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
TAPAS introduces an efficient, asymmetric two-server private aggregation scheme that significantly reduces computational and communication costs for large-scale federated learning compared to existing symmetric protocols.
The paper introduces a novel, scalable, and provably secure biometric authentication system designed to authenticate millions of users against cloud databases without requiring auxiliary identifiers.
The paper provides the first theoretical convergence analysis for machine learning training under fully homomorphic encryption combined with differential privacy, improving efficiency and scalability.
Papers
Revisiting ML Training under Fully Homomorphic Encryption: Convergence Guarantees, Differential Privacy, and Efficient Algorithms
Yvonne Zhou, Mingyu Liang, Ivan Brugere, Danial Dervovic +4 more
The paper provides the first theoretical convergence analysis for machine learning training under fully homomorphic encryption combined with differential privacy, improving efficiency and scalability.