Aleksander Mądry
Source-listed: Current OpenAI title not publicly named; MIT CSAIL lists Temporary Visiting Professor and PI · OpenAI (on leave from Massachusetts Institute of Technology)
Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.
Selected work
5- Towards Deep Learning Models Resistant to Adversarial AttacksSaved credit: Contributor · 2018Explore people connected to this work →
- Adversarial Examples Are Not Bugs, They Are FeaturesSaved credit: Contributor · 2019Explore people connected to this work →
- TRAK: Attributing Model Behavior at ScaleSaved credit: Contributor · 2023Explore people connected to this work →
- ContextCite: Attributing Model Generation to ContextSaved credit: Contributor · 2024Explore people connected to this work →
- Monitoring Reasoning Models for Misbehavior and the Risks of Promoting ObfuscationSaved credit: Contributor · 2025Explore people connected to this work →