Saved in:
Bibliographic Details
Main Authors: Razeghi, Behrooz, Rahimi, Parsa, Marcel, Sébastien
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2401.14792
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913211085750272
author Razeghi, Behrooz
Rahimi, Parsa
Marcel, Sébastien
author_facet Razeghi, Behrooz
Rahimi, Parsa
Marcel, Sébastien
contents In this study, we harness the information-theoretic Privacy Funnel (PF) model to develop a method for privacy-preserving representation learning using an end-to-end training framework. We rigorously address the trade-off between obfuscation and utility. Both are quantified through the logarithmic loss, a measure also recognized as self-information loss. This exploration deepens the interplay between information-theoretic privacy and representation learning, offering substantive insights into data protection mechanisms for both discriminative and generative models. Importantly, we apply our model to state-of-the-art face recognition systems. The model demonstrates adaptability across diverse inputs, from raw facial images to both derived or refined embeddings, and is competent in tasks such as classification, reconstruction, and generation.
format Preprint
id arxiv_https___arxiv_org_abs_2401_14792
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Deep Variational Privacy Funnel: General Modeling with Applications in Face Recognition
Razeghi, Behrooz
Rahimi, Parsa
Marcel, Sébastien
Computer Vision and Pattern Recognition
Information Theory
Machine Learning
In this study, we harness the information-theoretic Privacy Funnel (PF) model to develop a method for privacy-preserving representation learning using an end-to-end training framework. We rigorously address the trade-off between obfuscation and utility. Both are quantified through the logarithmic loss, a measure also recognized as self-information loss. This exploration deepens the interplay between information-theoretic privacy and representation learning, offering substantive insights into data protection mechanisms for both discriminative and generative models. Importantly, we apply our model to state-of-the-art face recognition systems. The model demonstrates adaptability across diverse inputs, from raw facial images to both derived or refined embeddings, and is competent in tasks such as classification, reconstruction, and generation.
title Deep Variational Privacy Funnel: General Modeling with Applications in Face Recognition
topic Computer Vision and Pattern Recognition
Information Theory
Machine Learning
url https://arxiv.org/abs/2401.14792