Exploiting Adversarial Embeddings for Better Steganography
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F19%3A00339848" target="_blank" >RIV/68407700:21230/19:00339848 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.1145/3335203.3335737" target="_blank" >https://doi.org/10.1145/3335203.3335737</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1145/3335203.3335737" target="_blank" >10.1145/3335203.3335737</a>
Alternative languages
Result language
angličtina
Original language name
Exploiting Adversarial Embeddings for Better Steganography
Original language description
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 minmax 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 perr 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.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2019
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the ACM Workshop on Information Hiding and Multimedia Security
ISBN
978-1-4503-6821-6
ISSN
—
e-ISSN
—
Number of pages
6
Pages from-to
216-221
Publisher name
ACM
Place of publication
New York
Event location
Paris
Event date
Jul 3, 2019
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—