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.

Juuti and colleagues · IEEE Euro S&P 2019 Research study

PRADA: Protecting against DNN Model Stealing Attacks (original source, new tab)

Tests query-pattern detection under specific assumptions; not proof of universal theft detection or typical detection delay.

Nevo and colleagues · RAND 2024 Research risk assessment

Securing AI Model Weights: Preventing Theft and Misuse of Frontier Models (original source, new tab)

Analyzes theft pathways and proposed security levels; not an inventory of confirmed theft incidents.

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.