Exploiting Adversarial Embeddings for ...
Document type :
Communication dans un congrès avec actes
DOI :
Title :
Exploiting Adversarial Embeddings for Better Steganography
Author(s) :
Bernard, Solène [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Pevný, Tomáš [Auteur]
Czech Technical University in Prague [CTU]
Bas, Patrick [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Klein, John [Auteur]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Pevný, Tomáš [Auteur]
Czech Technical University in Prague [CTU]
Bas, Patrick [Auteur]

Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Klein, John [Auteur]

Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189 [CRIStAL]
Conference title :
IH-MMSec
City :
Paris
Country :
France
Start date of the conference :
2019-07-03
Journal title :
IH&MMSec'19 Proceedings of the ACM Workshop on Information Hiding and Multimedia Security
English keyword(s) :
steganography
adversarial attacks
security
game-theory
adversarial attacks
security
game-theory
HAL domain(s) :
Sciences de l'ingénieur [physics]/Traitement du signal et de l'image [eess.SP]
English abstract : [en]
This work proposes a protocol to iteratively build a distortion function for adaptive steganography while increasing its practical security after each iteration. It relies on prior art on targeted attacks and iterative ...
Show more >This work proposes a protocol to iteratively build a distortion function for adaptive steganography while increasing its practical security after each iteration. It relies on prior art on targeted attacks and iterative design of steganalysis schemes. It combines targeted attacks on a given detector with a min max strategy, which dynamically selects the most difficult stego content associated with the best classifier at each iteration. We theoretically prove the convergence, which is confirmed by the practical results. Applied on J-Uniward this new protocol increases P err from 7% to 20% estimated by Xu-Net, and from 10% to 23% for a non-targeted steganalysis by a linear classifier with GFR features. CCS CONCEPTS • Security and privacy → Domain-specific security and privacy architectures;Show less >
Show more >This work proposes a protocol to iteratively build a distortion function for adaptive steganography while increasing its practical security after each iteration. It relies on prior art on targeted attacks and iterative design of steganalysis schemes. It combines targeted attacks on a given detector with a min max strategy, which dynamically selects the most difficult stego content associated with the best classifier at each iteration. We theoretically prove the convergence, which is confirmed by the practical results. Applied on J-Uniward this new protocol increases P err from 7% to 20% estimated by Xu-Net, and from 10% to 23% for a non-targeted steganalysis by a linear classifier with GFR features. CCS CONCEPTS • Security and privacy → Domain-specific security and privacy architectures;Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
ANR Project :
Collections :
Source :
Files
- https://hal.archives-ouvertes.fr/hal-02177259/document
- Open access
- Access the document
- https://hal.archives-ouvertes.fr/hal-02177259/document
- Open access
- Access the document
- https://hal.archives-ouvertes.fr/hal-02177259/document
- Open access
- Access the document
- document
- Open access
- Access the document
- main_final_HAL.pdf
- Open access
- Access the document
- document
- Open access
- Access the document
- main_final_HAL.pdf
- Open access
- Access the document