The evidence behind the guides

Sources

Find a study, check what it supports, and follow it back to a concern.

TopicCollection

2 sources

Guide citations are still under editorial review.

NIST · 2025 Technical report

Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations (original source, new tab)

Defines attack objectives and mechanisms across AI lifecycle stages. Taxonomy categories are not estimates of incident frequency.

Shafahi and colleagues · NeurIPS 2018 Research study

Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks (original source, new tab)

Demonstrates correctly labeled training examples causing selected classification errors under tested training arrangements.

Sources retain their original publishers’ rights. Inclusion does not imply endorsement. Saved sources stay in this browser on this device. Dates and source descriptions come from the existing editorial records.