Adversarial Attacks on Hyperbolic Networks
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F25%3A00378445" target="_blank" >RIV/68407700:21730/25:00378445 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.1007/978-3-031-91585-7_22" target="_blank" >https://doi.org/10.1007/978-3-031-91585-7_22</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1007/978-3-031-91585-7_22" target="_blank" >10.1007/978-3-031-91585-7_22</a>
Alternative languages
Result language
angličtina
Original language name
Adversarial Attacks on Hyperbolic Networks
Original language description
As hyperbolic deep learning grows in popularity, so does the need for adversarial robustness in the context of such a non-Euclidean geometry. To this end, this paper proposes hyperbolic alternatives to the commonly used FGM and PGD adversarial attacks. Through interpretable synthetic benchmarks and experiments on existing datasets, we show how the existing and newly proposed attacks differ. Moreover, we investigate the differences in adversarial robustness between Euclidean and fully hyperbolic networks. We find that these networks suffer from different types of vulnerabilities and that the newly proposed hyperbolic attacks cannot address these differences. Therefore, we conclude that the shifts in adversarial robustness are due to the models learning distinct patterns resulting from their different geometries.
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/EH22_008%2F0004590" target="_blank" >EH22_008/0004590: Robotics and advanced industrial production</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2025
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Computer Vision – ECCV 2024, Part XVII
ISBN
978-3-031-91584-0
ISSN
0302-9743
e-ISSN
1611-3349
Number of pages
19
Pages from-to
363-381
Publisher name
Springer
Place of publication
Cham
Event location
Milano
Event date
Sep 29, 2024
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
001544990200022