Leveraging Data Geometry to Mitigate CSM in Steganalysis
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F23%3A00375054" target="_blank" >RIV/68407700:21230/23:00375054 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.1109/WIFS58808.2023.10374944" target="_blank" >https://doi.org/10.1109/WIFS58808.2023.10374944</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/WIFS58808.2023.10374944" target="_blank" >10.1109/WIFS58808.2023.10374944</a>
Alternative languages
Result language
angličtina
Original language name
Leveraging Data Geometry to Mitigate CSM in Steganalysis
Original language description
In operational scenarios, steganographers use sets of covers from various sensors and processing pipelines that differ significantly from those used by researchers to train steganalysis models. This leads to an inevitable performance gap when dealing with out-of-distribution covers, commonly referred to as Cover Source Mismatch (CSM). In this study, we consider the scenario where test images are processed using the same pipeline. However, knowledge regarding both the labels and the balance between cover and stego is missing. Our objective is to identify a training dataset that allows for maximum generalization to our target. By exploring a grid of processing pipelines fostering CSM, we discovered a geometrical metric based on the chordal distance between subspaces spanned by DCTr features, that exhibits high correlation with operational regret while being not affected by the cover-stego balance. Our contribution lies in the development of a strategy that enables the selection or derivation of customized training datasets, enhancing the overall generalization performance for a given target. Experimental validation highlights that our geometry-based optimization strategy outperforms traditional atomistic methods given reasonable assumptions. Additional resources are available at github.com/RonyAbecidan/LeveragingGeometrytoMitigateCSM.
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
<a href="/en/project/GF19-29680L" target="_blank" >GF19-29680L: Game Over Eva(sion): Securing Deep Learning with Game Theory</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2023
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
IEEE International Workshop on Information Forensics and Security
ISBN
979-8-3503-2491-4
ISSN
2157-4766
e-ISSN
2157-4774
Number of pages
6
Pages from-to
—
Publisher name
IEEE Signal Processing Society
Place of publication
New Jersey
Event location
Nuremberg
Event date
Dec 4, 2023
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
001156967300024