Adversarial Machine Learning for Robust Cybersecurity

EasyChair Preprint 14015

Abstract

The field of cybersecurity faces increasing challenges due to the evolving nature of cyber threats. Adversarial machine learning (AML) has emerged as a promising approach to enhance the robustness of cybersecurity systems. This paper provides an overview of AML techniques and their applications in cybersecurity. It explores the concept of adversarial attacks and defenses, highlighting their significance in the context of cybersecurity. The paper also discusses the limitations and challenges associated with AML, such as the need for large and diverse datasets, interpretability of models, and the trade-off between accuracy and robustness. Moreover, it presents potential future directions in AML research, including the integration of human expertise and the development of proactive defense mechanisms. Overall, this paper aims to shed light on the importance of AML in addressing the ever-growing cybersecurity threats and serves as a foundation for further research in this field.

Keyphrases: Adversarial, learning, machine

@booklet{EasyChair:14015,
  author    = {Kaledio Potter and Dylan Stilinki and Ralph Shad},
  title     = {Adversarial Machine Learning for Robust Cybersecurity},
  howpublished = {EasyChair Preprint 14015},
  year      = {EasyChair, 2024}}