Adversarial Robustness of Neural Networks from the Perspective of Lipschitz Calculus: A Survey
ACM Computing Surveys · 30.06.2025 · 57 (6) · 1-41
DOI: 10.1145/3648351 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 10.02.2025. Verfasst von Monty-Maximilian Zühlke und 1 weiteren Autor:innen. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 132 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Lower Saxony Ministry of Science and Culture, Lower Saxony “Vorab” of the Volkswagen Foundation and supported by the Center for Digital Innovations.
Abstract (Originalsprache)
We survey the adversarial robustness of neural networks from the perspective of Lipschitz calculus in a unifying fashion by expressing models, attacks and safety guarantees—that is, a notion of measurable trustworthiness—in a mathematical language. After an intuitive motivation, we discuss algorithms to estimate a network’s Lipschitz constant, Lipschitz regularisation techniques, robustness guarantees, and the connection between a model’s Lipschitz constant and its generalisation capabilities. Afterwards, we present a new vantage point regarding minimal Lipschitz extensions, corroborate its value empirically and discuss possible research directions. Finally, we add a toolbox containing mathematical prerequisites for navigating the field (Appendix).
Förderung
- Lower Saxony Ministry of Science and Culture
- Lower Saxony “Vorab” of the Volkswagen Foundation and supported by the Center for Digital Innovations
Zitieren
APA
Zühlke, M., & Kudenko, D. (2025). Adversarial Robustness of Neural Networks from the Perspective of Lipschitz Calculus: A Survey. ACM Computing Surveys, 57(6), 1-41. https://doi.org/10.1145/3648351
Vancouver
Zühlke M, Kudenko D. Adversarial Robustness of Neural Networks from the Perspective of Lipschitz Calculus: A Survey. ACM Computing Surveys. 2025;57(6):1-41. doi:10.1145/3648351
BibTeX
@article{Zhlke2025,
author = {Zühlke, Monty-Maximilian and Kudenko, Daniel},
title = {Adversarial Robustness of Neural Networks from the Perspective of Lipschitz Calculus: A Survey},
journal = {ACM Computing Surveys},
year = {2025},
volume = {57},
number = {6},
pages = {1--41},
doi = {10.1145/3648351}
}
EUVIMED