Published February 9, 2025 | Version 1.0
Publication Open

Adversarial Machine Learning: A Comprehensive Review of Cyber Threats and Defensive Strategies

Authors/Creators

  • 1. Independent Researcher

Description

This paper presents a detailed survey of adversarial attacks on machine learning models and corresponding defense mechanisms. It covers various attack vectors, including evasion and poisoning attacks, their impact on AI-driven systems, and state-of-the-art defensive strategies. Additionally, the paper discusses real-world applications and ethical considerations in adversarial AI research.

Files

Adversarial-Machine-Learning-A-Comprehensive-Review-of-Cyber-Threats-and-Defensive-Strategies-Behzad-Qasemi.pdf

Files (25.2 kB)

Additional details

Dates

Updated
2025-02-09

References

  • Papernot, N., McDaniel, P., & Goodfellow, I. (2016). Transferability in machine learning: from phenomena to black-box attacks using adversarial samples. arXiv preprint arXiv:1605.07277.
  • Carlini, N., & Wagner, D. (2017). Towards evaluating the robustness of neural networks. IEEE Symposium on Security and Privacy (SP).
  • Goodfellow, I., Shlens, J., & Szegedy, C. (2015). Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572.