Lightweight privacy-preserving GAN framework for model training and image synthesis

• Main Authors: YANG, Yang, MU, Ke, DENG, Robert H.
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2022
• Subjects: Protocols; Generative adversarial networks; Training; Cryptography; Computational modeling; Image synthesis; Privacy; Privacy-preserving; generative adversarial network; secret sharing; secure computation; deep learning; Information Security
• Online Access: https://ink.library.smu.edu.sg/sis_research/7247
• Institution: Singapore Management University

Generative adversarial network (GAN) has excellent performance for data generation and is widely used in image synthesis. Outsourcing GAN to cloud platform is a popular way to save local computation resources and improve the efficiency, but it still faces the privacy leakage concerns: (1) the sensit...