Saved in:
Bibliographic Details
Main Authors: Labiad, Ismail, Bäck, Thomas, Fernandez, Pierre, Najman, Laurent, Sander, Tom, Ye, Furong, Zameshina, Mariia, Teytaud, Olivier
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.15119
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909325153271808
author Labiad, Ismail
Bäck, Thomas
Fernandez, Pierre
Najman, Laurent
Sander, Tom
Ye, Furong
Zameshina, Mariia
Teytaud, Olivier
author_facet Labiad, Ismail
Bäck, Thomas
Fernandez, Pierre
Najman, Laurent
Sander, Tom
Ye, Furong
Zameshina, Mariia
Teytaud, Olivier
contents In many cases, adversarial attacks are based on specialized algorithms specifically dedicated to attacking automatic image classifiers. These algorithms perform well, thanks to an excellent ad hoc distribution of initial attacks. However, these attacks are easily detected due to their specific initial distribution. We therefore consider other black-box attacks, inspired from generic black-box optimization tools, and in particular the log-normal algorithm. We apply the log-normal method to the attack of fake detectors, and get successful attacks: importantly, these attacks are not detected by detectors specialized on classical adversarial attacks. Then, combining these attacks and deep detection, we create improved fake detectors.
format Preprint
id arxiv_https___arxiv_org_abs_2409_15119
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Log-normal Mutations and their Use in Detecting Surreptitious Fake Images
Labiad, Ismail
Bäck, Thomas
Fernandez, Pierre
Najman, Laurent
Sander, Tom
Ye, Furong
Zameshina, Mariia
Teytaud, Olivier
Artificial Intelligence
In many cases, adversarial attacks are based on specialized algorithms specifically dedicated to attacking automatic image classifiers. These algorithms perform well, thanks to an excellent ad hoc distribution of initial attacks. However, these attacks are easily detected due to their specific initial distribution. We therefore consider other black-box attacks, inspired from generic black-box optimization tools, and in particular the log-normal algorithm. We apply the log-normal method to the attack of fake detectors, and get successful attacks: importantly, these attacks are not detected by detectors specialized on classical adversarial attacks. Then, combining these attacks and deep detection, we create improved fake detectors.
title Log-normal Mutations and their Use in Detecting Surreptitious Fake Images
topic Artificial Intelligence
url https://arxiv.org/abs/2409.15119