Research Areas
Fully Homomorphic Encryption
A cryptographic technique that enables computations on encrypted data without decryption. I study its practical integration into privacy-preserving machine learning systems.
Federated Learning
A distributed learning approach where data remains on local devices. My work focuses on securing model updates using cryptographic protections against information leakage.
Privacy-Preserving Technologies
Methods that allow data to be used while preserving confidentiality. I explore efficient privacy-enhancing techniques for real-world federated and distributed systems.