Article (Scientific journals)
Evasion Attack STeganography: Turning Vulnerability Of Machine Learning ToAdversarial Attacks Into A Real-world Application
Ghamizi, Salah; Cordy, Maxime; Papadakis, Mike et al.
2021In Proceedings of International Conference on Computer Vision 2021
Peer reviewed
 

Files


Full Text
EAST_ICCV_CameraReady.pdf
Author postprint (1.48 MB)
Request a copy

All documents in ORBilu are protected by a user license.

Send to



Details



Keywords :
Adversarial Attacks; Steganography; Watermarking
Abstract :
[en] Evasion Attacks have been commonly seen as a weakness of Deep Neural Networks. In this paper, we flip the paradigm and envision this vulnerability as a useful application. We propose EAST, a new steganography and watermarking technique based on multi-label targeted evasion attacks. Our results confirm that our embedding is elusive; it not only passes unnoticed by humans, steganalysis methods, and machine-learning detectors. In addition, our embedding is resilient to soft and aggressive image tampering (87% recovery rate under jpeg compression). EAST outperforms existing deep-learning-based steganography approaches with images that are 70% denser and 73% more robust and supports multiple datasets and architectures.
Disciplines :
Computer science
Author, co-author :
Ghamizi, Salah ;  University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS)
Cordy, Maxime  ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SerVal
Papadakis, Mike ;  University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS)
Le Traon, Yves ;  University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > SerVal
External co-authors :
no
Language :
English
Title :
Evasion Attack STeganography: Turning Vulnerability Of Machine Learning ToAdversarial Attacks Into A Real-world Application
Publication date :
11 October 2021
Journal title :
Proceedings of International Conference on Computer Vision 2021
Peer reviewed :
Peer reviewed
Focus Area :
Security, Reliability and Trust
Available on ORBilu :
since 16 August 2021

Statistics


Number of views
281 (45 by Unilu)
Number of downloads
4 (2 by Unilu)

Scopus citations®
 
4
Scopus citations®
without self-citations
3
WoS citations
 
2

Bibliography


Similar publications



Contact ORBilu