NIST Adversarial Machine Learning Taxonomy 2025

Research question

How should attacks and mitigations on predictive and generative AI be classified?

Key findings

Separate taxonomies for predictive AI (evasion, poisoning, privacy) and generative AI (supply chain, direct and indirect prompt injection, misuse) - Catalogues mitigations and their limitations for each attack class

Sources

doi.orghttps://doi.org/10.6028/NIST.AI.100-2e2025

Contribute

Spot an error, or know a record we should add? Members can propose additions and submit corrections.

Submit research Report a correction or request removal

Related in Research Paper Library

The More It Says, the More You Pay: A Black-Box Audit of Provider-Side Token Inflation in LLM Services

In pay-per-token LLM services, the more a model says, the more users pay. Dishonest providers can covertly manipulate generation to inflate output tokens while largely preserving task utility. We define such…

Adversarial examples and evasion2026

A GAN-Based Framework for Robust DDoS Attack Detection

The availability and consistency of online services remain vulnerable due to Distributed Denial of Service (DDoS) attacks. These attacks are evolving by adopting more complex strategies to evade traditional network…

Adversarial examples and evasion2026

When Agents Look Like Beacons: NIDS Evasion by Model Context Protocol Traffic

The Model Context Protocol (MCP) standardizes communication between autonomous Artificial Intelligence (AI) agents and remote tools over Streamable HTTP. This shift introduces a class of machine-generated,…

Adversarial examples and evasion2026