Salvato in:
Dettagli Bibliografici
Autori principali: Anderson, Kathleen, Martinetz, Thomas
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2503.09306
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916650798809088
author Anderson, Kathleen
Martinetz, Thomas
author_facet Anderson, Kathleen
Martinetz, Thomas
contents We evaluate the information that can unintentionally leak into the low dimensional output of a neural network, by reconstructing an input image from a 40- or 32-element feature vector that intends to only describe abstract attributes of a facial portrait. The reconstruction uses blackbox-access to the image encoder which generates the feature vector. Other than previous work, we leverage recent knowledge about image generation and facial similarity, implementing a method that outperforms the current state-of-the-art. Our strategy uses a pretrained StyleGAN and a new loss function that compares the perceptual similarity of portraits by mapping them into the latent space of a FaceNet embedding. Additionally, we present a new technique that fuses the output of an ensemble, to deliberately generate specific aspects of the recreated image.
format Preprint
id arxiv_https___arxiv_org_abs_2503_09306
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Revealing Unintentional Information Leakage in Low-Dimensional Facial Portrait Representations
Anderson, Kathleen
Martinetz, Thomas
Computer Vision and Pattern Recognition
We evaluate the information that can unintentionally leak into the low dimensional output of a neural network, by reconstructing an input image from a 40- or 32-element feature vector that intends to only describe abstract attributes of a facial portrait. The reconstruction uses blackbox-access to the image encoder which generates the feature vector. Other than previous work, we leverage recent knowledge about image generation and facial similarity, implementing a method that outperforms the current state-of-the-art. Our strategy uses a pretrained StyleGAN and a new loss function that compares the perceptual similarity of portraits by mapping them into the latent space of a FaceNet embedding. Additionally, we present a new technique that fuses the output of an ensemble, to deliberately generate specific aspects of the recreated image.
title Revealing Unintentional Information Leakage in Low-Dimensional Facial Portrait Representations
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.09306