A. Feder Cooper

Venues

Frequent coauthors

Papers

1. Comparison requires valid measurement: Rethinking attack success rate comparisons in AI red teaming
   NeurIPS 2025 ·

   Alexandra Chouldechova

   DBLP profile ↗ORCID search ↗
2. Exploring the limits of strong membership inference attacks on large language models
   NeurIPS 2025 ·

   Jamie Hayes

   DBLP profile ↗ORCID search ↗
3. Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research
   NeurIPS 2025 · A. Feder Cooper
4. Measuring memorization in language models via probabilistic extraction
   NAACL 2025 ·

   Jamie Hayes

   DBLP profile ↗ORCID search ↗
5. Position: Evaluating Generative AI Systems Is a Social Science Measurement Challenge
   ICML 2025 ·

   Hanna M. Wallach

   DBLP profile ↗ORCID search ↗
6. Scalable Extraction of Training Data from Aligned, Production Language Models
   ICLR 2025 ·

   Milad Nasr

   DBLP profile ↗ORCID search ↗
7. The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text
   NeurIPS 2025 ·

   Nikhil Kandpal

   DBLP profile ↗ORCID search ↗
8. Arbitrariness and Social Prediction: The Confounding Role of Variance in Fair Classification
   AAAI 2024 · A. Feder Cooper
9. Common Canvas: Open Diffusion Models Trained on Creative-Commons Images
   CVPR 2024 ·

   Aaron Gokaslan

   DBLP profile ↗ORCID search ↗
10. Position: Standardization of Behavioral Use Clauses is Necessary for the Adoption of Responsible Licensing of AI
    ICML 2024 ·

    Daniel McDuff

    DBLP profile ↗ORCID search ↗
11. Stealing part of a production language model
    ICML 2024 ·

    Nicholas Carlini

    DBLP profile ↗ORCID search ↗