% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@ARTICLE{Weigand:636102,
author = {Weigand, Lukas and Roith, Tim and Burger, Martin},
title = {{A}dversarial flows: {A} gradient flow characterization of
adversarial attacks},
journal = {European journal of applied mathematics},
volume = {37},
number = {1},
issn = {0956-7925},
address = {Cambridge},
publisher = {Cambridge Univ. Press},
reportid = {PUBDB-2025-03598, arXiv:2406.05376},
pages = {123 - 179},
year = {2025},
abstract = {A popular method to perform adversarial attacks on neuronal
networks is the so-called fast gradient sign method and its
iterative variant. In this paper, we interpret this method
as an explicit Euler discretization of a differential
inclusion, where we also show convergence of the
discretization to the associated gradient flow. To do so, we
consider the concept of p-curves of maximal slope in the
case $p=\infty$. We prove existence of $\infty$-curves of
maximum slope and derive an alternative characterization via
differential inclusions. Furthermore, we also consider
Wasserstein gradient flows for potential energies, where we
show that curves in the Wasserstein space can be
characterized by a representing measure on the space of
curves in the underlying Banach space, which fulfill the
differential inclusion. The application of our theory to the
finite-dimensional setting is twofold: On the one hand, we
show that a whole class of normalized gradient descent
methods (in particular signed gradient descent) converge, up
to subsequences, to the flow, when sending the step size to
zero. On the other hand, in the distributional setting, we
show that the inner optimization task of adversarial
training objective can be characterized via $\infty$-curves
of maximum slope on an appropriate optimal transport space.},
cin = {FS-CI},
ddc = {510},
cid = {I:(DE-H253)FS-CI-20230420},
pnm = {623 - Data Management and Analysis (POF4-623)},
pid = {G:(DE-HGF)POF4-623},
experiment = {EXP:(DE-MLZ)NOSPEC-20140101},
typ = {PUB:(DE-HGF)16},
eprint = {2406.05376},
howpublished = {arXiv:2406.05376},
archivePrefix = {arXiv},
SLACcitation = {$\%\%CITATION$ = $arXiv:2406.05376;\%\%$},
doi = {10.1017/S0956792525100120},
url = {https://bib-pubdb1.desy.de/record/636102},
}