Abstract
Recent studies have shown that Machine Learning (ML) algorithm suffers from several vulnerability threats. Among them, adversarial attacks represent one of the most critical issues. This chapter provides an overview of the ML vulnerability challenges, with a focus on the security threats for Deep Neural Networks, Capsule Networks, and Spiking Neural Networks. Moreover, it discusses the current trends and outlooks on the methodologies for enhancing the ML models’ robustness.
Original language | English (US) |
---|---|
Title of host publication | Embedded Machine Learning for Cyber-Physical, IoT, and Edge Computing |
Subtitle of host publication | Use Cases and Emerging Challenges |
Publisher | Springer Nature |
Pages | 463-496 |
Number of pages | 34 |
ISBN (Electronic) | 9783031406775 |
ISBN (Print) | 9783031406768 |
DOIs | |
State | Published - Jan 1 2023 |
Keywords
- Adversarial attacks
- Capsule Networks
- Deep Neural Networks
- Machine learning security
- Robustness
- Spiking Neural Networks
ASJC Scopus subject areas
- General Computer Science
- General Engineering
- General Social Sciences