About this document
Securing ML: Adversarial Attacks & Bias by International Journal of Innovative Science and Research Technology is a document available to read on EtoBox.
This paper offers a comprehensive examination of adversarial vulnerabilities in machine learning (ML) models and strategies for mitigating fairness and bias issues. It analyses various adversarial attack vectors encompassing evasion, poisoning, model inversion, exploratory probes, and model stealing, elucidating their potential to compromise model integrity and induce misclassification or information leakage.
- Author
- International Journal of Innovative Science and Research Technology
- Language
- EN