|
Original research PRIVACY-PRESERVING MACHINE LEARNING ON ENCRYPTED DATA USING HOMOMORPHIC ENCRYPTIONPages 71-76
Sandesh Kokad, Prathamesh Adawale, Pravin Shinde,
Abstract
The rising adoption of machine learning (ML) across various industries has sparked concerns due to the sensitive nature of the data involved and the opacity surrounding its collection, aggregation, and sharing practices. To address these concerns, researchers are actively developing methods to mitigate privacy risks associated with ML applications. One such approach involves integrating privacy-preserving mechanisms into active learning techniques. By leveraging homomorphic encryption-based federated learning, which enables distributed computation across multiple clients while maintaining strong data privacy, researchers have proposed a scheme that safeguards user data privacy in active learning scenarios. Experimental results indicate that this approach effectively preserves privacy while maintaining model accuracy. Additionally, a comparison with other schemes highlights its superiority in mitigating gradient leakage, with the proposed scheme exhibiting no gradient leakage compared to alternatives that suffer from significant leakage rates exceeding 74%. Keywords: Privacy-preserving machine learning, Homomorphic encryption, Encrypted data, Data privacy, Machine learning [ML] algorithms.
|
Harsha Patil, 
PDF 