Interpretable Machine Learning for Privacy-Preserving Pervasive Systems
This addresses privacy concerns for users of pervasive systems, but it appears incremental as it focuses on interpretability without introducing new privacy-preserving methods.
The paper tackles the problem of privacy violations in pervasive systems by proposing an interpretability framework that helps users understand how their data traces are used, but it does not provide concrete results or numbers.
Our everyday interactions with pervasive systems generate traces that capture various aspects of human behavior and enable machine learning algorithms to extract latent information about users. In this paper, we propose a machine learning interpretability framework that enables users to understand how these generated traces violate their privacy.