Deep Privacy Funnel Model: From a Discriminative to a Generative Approach with an Application to Face Recognition

arXiv:2404.02696v1 Announce Type: new
Abstract: In this study, we apply the information-theoretic Privacy Funnel (PF) model to the domain of face recognition, developing a novel method for privacy-preserving representation learning within an end-to-end training framework. Our approach addresses the trade-off between obfuscation and utility in data protection, quantified through logarithmic loss, also known as self-information loss. This research provides a foundational exploration into the integration of information-theoretic privacy principles with representation learning, focusing specifically on the face recognition systems. We …

abstract application apply arxiv cs.lg domain face face recognition framework generative information novel privacy recognition representation representation learning study the information trade trade-off training type