AnonyNoise: Anonymizing Event Data with Smart Noise to Outsmart Re-Identification and Preserve Privacy

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bendig, Katharina, Schuster, René, Thiemer, Nicole, Joisten, Karen, Stricker, Didier
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913585269047296
author Bendig, Katharina
Schuster, René
Thiemer, Nicole
Joisten, Karen
Stricker, Didier
author_facet Bendig, Katharina
Schuster, René
Thiemer, Nicole
Joisten, Karen
Stricker, Didier
contents The increasing capabilities of deep neural networks for re-identification, combined with the rise in public surveillance in recent years, pose a substantial threat to individual privacy. Event cameras were initially considered as a promising solution since their output is sparse and therefore difficult for humans to interpret. However, recent advances in deep learning proof that neural networks are able to reconstruct high-quality grayscale images and re-identify individuals using data from event cameras. In our paper, we contribute a crucial ethical discussion on data privacy and present the first event anonymization pipeline to prevent re-identification not only by humans but also by neural networks. Our method effectively introduces learnable data-dependent noise to cover personally identifiable information in raw event data, reducing attackers' re-identification capabilities by up to 60%, while maintaining substantial information for the performing of downstream tasks. Moreover, our anonymization generalizes well on unseen data and is robust against image reconstruction and inversion attacks. Code: https://github.com/dfki-av/AnonyNoise
format Preprint
id arxiv_https___arxiv_org_abs_2411_16440
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AnonyNoise: Anonymizing Event Data with Smart Noise to Outsmart Re-Identification and Preserve Privacy
Bendig, Katharina
Schuster, René
Thiemer, Nicole
Joisten, Karen
Stricker, Didier
Computer Vision and Pattern Recognition
The increasing capabilities of deep neural networks for re-identification, combined with the rise in public surveillance in recent years, pose a substantial threat to individual privacy. Event cameras were initially considered as a promising solution since their output is sparse and therefore difficult for humans to interpret. However, recent advances in deep learning proof that neural networks are able to reconstruct high-quality grayscale images and re-identify individuals using data from event cameras. In our paper, we contribute a crucial ethical discussion on data privacy and present the first event anonymization pipeline to prevent re-identification not only by humans but also by neural networks. Our method effectively introduces learnable data-dependent noise to cover personally identifiable information in raw event data, reducing attackers' re-identification capabilities by up to 60%, while maintaining substantial information for the performing of downstream tasks. Moreover, our anonymization generalizes well on unseen data and is robust against image reconstruction and inversion attacks. Code: https://github.com/dfki-av/AnonyNoise
title AnonyNoise: Anonymizing Event Data with Smart Noise to Outsmart Re-Identification and Preserve Privacy
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.16440