Dynamic-Max-Value ReLU Functions for Adversarially Robust Machine Learning Models
Mathematics · 13.11.2024 · 12 (22) · 3551
DOI: 10.3390/math12223551 ↗Kurz gefasst
Fachartikel in der Zeitschrift Mathematics, online erschienen am 13.11.2024. Verfasst von Korn Sooksatra und 1 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation.
Abstract (Originalsprache)
The proliferation of deep learning has transformed artificial intelligence, demonstrating prowess in domains such as image recognition, natural language processing, and robotics. Nonetheless, deep learning models are susceptible to adversarial examples, well-crafted inputs that can induce erroneous predictions, particularly in safety-critical contexts. Researchers actively pursue countermeasures such as adversarial training and robust optimization to fortify model resilience. This vulnerability is notably accentuated by the ubiquitous utilization of ReLU functions in deep learning models. A previous study proposed an innovative solution to mitigate this vulnerability, presenting a capped ReLU function tailored to bolster neural network robustness against adversarial examples. However, the approach had a scalability problem. To address this limitation, a series of comprehensive experiments are undertaken across diverse datasets, and we introduce the dynamic-max-value ReLU function to address the scalability problem.
Förderung
- National Science Foundation
Zitieren
APA
Sooksatra, K., & Rivas, P. (2024). Dynamic-Max-Value ReLU Functions for Adversarially Robust Machine Learning Models. Mathematics, 12(22), 3551. https://doi.org/10.3390/math12223551
Vancouver
Sooksatra K, Rivas P. Dynamic-Max-Value ReLU Functions for Adversarially Robust Machine Learning Models. Mathematics. 2024;12(22):3551. doi:10.3390/math12223551
BibTeX
@article{Sooksatra2024,
author = {Sooksatra, Korn and Rivas, Pablo},
title = {Dynamic-Max-Value ReLU Functions for Adversarially Robust Machine Learning Models},
journal = {Mathematics},
year = {2024},
volume = {12},
number = {22},
pages = {3551},
doi = {10.3390/math12223551}
}
EUVIMED