Compressive Privacy Generative Adversarial Network

• Published in: IEEE transactions on information forensics and security Vol. 15; pp. 2499 - 2513
• Main Authors: Tseng, Bo-Wei, Wu, Pei-Yuan
• Format: Journal Article
• Language: English
• Published: New York IEEE 2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: adversarial learning; Compression tests; Compressive privacy; cyber security; Data models; Data privacy; Feature extraction; Generative adversarial networks; Machine learning; machine learning as a service; Privacy; privacy preserving machine learning; Privatization; Stochastic processes
• ISSN: 1556-6013; 1556-6021
• DOI: 10.1109/TIFS.2020.2968188

Machine learning as a service (MLaaS) has brought much convenience to our daily lives recently. However, the fact that the service is provided through cloud raises privacy leakage issues. In this work we propose the compressive privacy generative adversarial network (CPGAN), a data-driven adversarial learning framework for generating compressing representations that retain utility comparable to state-of-the-art, with the additional feature of defending against reconstruction attack. This is achieved by applying adversarial learning scheme to the design of compression network (privatizer), whose utility/privacy performances are evaluated by the utility classifier and the adversary reconstructor, respectively. Experimental results demonstrate that CPGAN achieves better utility/privacy trade-off in comparison with the previous work, and is applicable to real-world large datasets.