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.

Sadasivan and colleagues Research study

Can AI-Generated Text be Reliably Detected? (original source, new tab)

Examines theoretical and empirical detection limits; does not establish that every detection task is impossible.

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.