Protecting Sensitive Attributes by Adversarial Training Through Class-Overlapping Techniques
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Transactions on Information Forensics and Security"
DOI: 10.1109/tifs.2023.3236180
Abstract: In recent years, machine learning as a service (MLaaS) has brought considerable convenience to our daily lives. However, these services raise the issue of leaking users’ sensitive attributes, such as race, when provided through the… read more here.
Keywords: attributes adversarial; sensitive attributes; class overlapping; class ... See more keywords