1 source
Co-authored “Adversarial Examples Are Not Bugs, They Are Features”.
Researcher Profile
Andrew Ilyas
Adversarial robustness and feature learning
Researcher at Stanford Medicine
Co-authored “Adversarial Examples Are Not Bugs, They Are Features”.
Organizations
Stanford Medicine
About This Page
This profile is meant to help you get oriented quickly: why this researcher matters, what to read first, and where to explore next.
Last updated
March 20, 2026
Best First Clicks
Official And External Links
Known For
The ideas, systems, and research directions that make this person worth knowing.
01
Adversarial robustness and feature learning
02
Adversarial Examples Are Not Bugs, They Are Features
03
Robustness
04
Adversarial ML
Start Here
Canonical papers, project pages, or repositories that anchor this profile.
Signature Works
Additional papers, projects, or repositories that help flesh out the profile.
Supporting Sources
Additional links that help verify and flesh out this profile.
Related Researchers
People worth exploring next because they share topics, labs, or source material with this profile.
1 source
Co-authored “Adversarial Examples Are Not Bugs, They Are Features”.
1 source
Co-authored “Adversarial Examples Are Not Bugs, They Are Features”.
4 sources
One of the most useful people to study if you care about what deployed models get wrong under pressure, especially around extraction, adversarial behavior, and practical security failures.
1 source
Co-authored Red Teaming LMs with LMs: a concrete approach to stress-testing model behavior at scale.
1 source
Co-authored Red Teaming LMs with LMs: a concrete approach to stress-testing model behavior at scale.