Semantic Adversarial Attacks for Privacy Protection

A Google TechTalk, 2020/7/30, presented byAli Shahin Shamsabadi, Ricardo Sanchez-Matilla, Andrea Cavallaro, Queen Mary University of London ABSTRACT: Images shared on social media are routinely analyzed by machine learning models for content annotation and user profiling. These automatic inferences reveal to the service provider sensitive information that a naive user might want to keep private. The unwanted inference of trained machine learning models can be prevented via data modification. We show how to modify images, while maintaining or even enhancing their visual quality, prior to sharing them online, so that classifiers cannot infer private information from the visual content.