Directory /

Nicholas Carlini

x · Follow ↗

AI system securityResponsible AI & harms

Adversarial ML, model extraction, privacy and attacks

Type
Security researcher
Priority
Tier 1 · core
Perspective
Academic security
Best for
Research papers and rigorous critiques
Publishes
Recurring
Editor's note
Prefer linked papers and code for source-of-record evidence.
The AI Safety & Security brief

Get the useful signal in your inbox.

Sign up for updates on original analysis of AI safety, agent security and governance.

Addresses are saved for this newsletter. Email delivery is being set up; you can also follow the RSS feed.