Artificial Intelligence Security and Adversarial Machine Learning: Threat Models, Defensive Strategies, and Forensic Implications for Trustworthy AI Systems

Abstract

The rapid integration of artificial intelligence (AI) systems into security-critical domains has introduced new vulnerabilities, exposing these systems to a growing spectrum of adversarial threats. Adversarial machine learning (AML) has emerged as a key area of research aimed at understanding and mitigating these risks. This paper presents a structured synthesis of AML threat models, defensive mechanisms, and the forensic implications essential for trustworthy AI deployment. We systematically ca

Categories

@misc{senanu2026artificial,
  title = {{Artificial Intelligence Security and Adversarial Machine Learning: Threat Models, Defensive Strategies, and Forensic Implications for Trustworthy AI Systems}},
  author = {James H. Senanu},
  year = {2026},
  doi = {10.2139/ssrn.6144306},
  url = {https://doi.org/10.2139/ssrn.6144306}
}