It Is All about Data: A Survey on the Effects of Data on Adversarial Robustness
ACM Computing Surveys · 31.07.2024 · 56 (7) · 1-41
DOI: 10.1145/3627817 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 09.04.2024. Verfasst von Peiyu Xiong und 4 weiteren Autor:innen. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 189 Literaturangaben.
Abstract (Originalsprache)
Adversarial examples are inputs to machine learning models that an attacker has intentionally designed to confuse the model into making a mistake. Such examples pose a serious threat to the applicability of machine learning-based systems, especially in life- and safety-critical domains. To address this problem, the area of adversarial robustness investigates mechanisms behind adversarial attacks and defenses against these attacks. This survey reviews a particular subset of this literature that focuses on investigating properties of training data in the context of model robustness under evasion attacks. It first summarizes the main properties of data leading to adversarial vulnerability. It then discusses guidelines and techniques for improving adversarial robustness by enhancing the data representation and learning procedures, as well as techniques for estimating robustness guarantees given particular data. Finally, it discusses gaps of knowledge and promising future research directions in this area.
Zitieren
APA
Xiong, P., Tegegn, M., Sarin, J. S., Pal, S., & Rubin, J. (2024). It Is All about Data: A Survey on the Effects of Data on Adversarial Robustness. ACM Computing Surveys, 56(7), 1-41. https://doi.org/10.1145/3627817
Vancouver
Xiong P, Tegegn M, Sarin JS, Pal S, Rubin J. It Is All about Data: A Survey on the Effects of Data on Adversarial Robustness. ACM Computing Surveys. 2024;56(7):1-41. doi:10.1145/3627817
BibTeX
@article{Xiong2024,
author = {Xiong, Peiyu and Tegegn, Michael and Sarin, Jaskeerat Singh and Pal, Shubhraneel and Rubin, Julia},
title = {It Is All about Data: A Survey on the Effects of Data on Adversarial Robustness},
journal = {ACM Computing Surveys},
year = {2024},
volume = {56},
number = {7},
pages = {1--41},
doi = {10.1145/3627817}
}
EUVIMED