Dynamic-Max-Value ReLU Functions for Adversarially Robust Machine Learning Models

Korn Sooksatra () and Pablo Rivas ()
Additional contact information
Korn Sooksatra: Department of Computer Science, Baylor University, Waco, TX 76706, USA
Pablo Rivas: Department of Computer Science, Baylor University, Waco, TX 76706, USA

Mathematics, 2024, vol. 12, issue 22, 1-40

Abstract: 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.

Keywords: machine learning; adversarial machine learning; robustness; trustworthy AI; adversarial examples (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/12/22/3551/pdf (application/pdf)
https://www.mdpi.com/2227-7390/12/22/3551/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:12:y:2024:i:22:p:3551-:d:1520271

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().