Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations (NIST AI 100-2e2025)

Apostol Vassilev, Alina Oprea, Alie Fordyce, Hyrum Anderson

Abstract

NIST's authoritative taxonomy of adversarial ML attacks and mitigations covering evasion, poisoning, privacy, and abuse attacks against AI systems.

Categories

Tags

Framework Mappings

Cite This Resource

@article{llmsec202400040,
  title = {Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations (NIST AI 100-2e2025)},
  author = {Apostol Vassilev and Alina Oprea and Alie Fordyce and Hyrum Anderson},
  year = {2024},
  journal = {NIST},
  url = {https://csrc.nist.gov/pubs/ai/100/2/e2025/final},
}