← Back
media
Adversarial Examples Are Not Bugs, They Are Features
Last discussed Oct 26, 2026
A machine learning research paper by Aleksander Madry's group at MIT arguing that adversarial vulnerability arises from non-robust but predictive features in data.
Recently discussed in
AI Crisis in Math: Navier-Stokes, Riemann Hypothesis & Complexity Theory | Lex Fridman Podcast #503
Ankur Moitra · Oct 26, 2026
What creators say
AM
Ankur Moitra
mentioned
Praised: A cool experiment showing that deep networks rely on statistical patterns hum...
"I had a former colleague at MIT, Alex Madry, that had some really nice work, which I really enjoyed. I think the title was something like 'Adversarial Examples Are Features, Not Bugs.' So they did the following cool experiment."
More from Ankur Moitra →Keep exploring
Topics
About this data
- ✓48,000+ mentions extracted from real podcast transcripts
- ✓Every quote links to the source episode
- ✓Sponsored mentions are always labeled
- ✓Critical takes are shown, never filtered out
Get an email when a new creator recommends it