Metrics
4 Record Views
Book chapter
Homology as an Adversarial Attack Indicator
Adversary-Aware Learning Techniques and Trends in Cybersecurity, pp.167-196
Springer International Publishing
2021
Abstract
In this paper we show how classical topological information can be automated with machine learning to lessen the threat of an adversarial attack. This paper is a proof of concept which lays the groundwork for future research in this area.
Related links
Details
- Title
- Homology as an Adversarial Attack Indicator
- Publication Details
- Adversary-Aware Learning Techniques and Trends in Cybersecurity, pp.167-196
- Resource Type
- Book chapter
- Publisher
- Springer International Publishing; Cham
- Copyright
- This is a U.S. government work and not under copyright protection in the U.S.; foreign copyright protection may apply 2021
- Identifiers
- 99381512425706600
- Academic Unit
- Intelligent Systems and Robotics; Hal Marcus College of Science and Engineering
- Language
- English