Elamur Research⌕
☰
home / authors / Matt Fredrikson

Matt Fredrikson

Matt Fredrikson has 2 papers in our library, in 2017–2023, most of them on Language models & pretraining, Bias, fairness & safety; often with Andy Zou, J. Zico Kolter, Milad Nasr.

2 papers in our library · 2017–2023

OpenAlex · ORCID · Wikidata · h-index 28 · 122 works · 10,483 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 Cited 1,295 times in our library · 2 more in our library without a page yet · ⭐ Paper Stars ranking: #1468

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓Carnegie Mellon UniversityPittsburgh · United States2015–2026 · 61 papersEmployment since 2015 · Associate Professor, Computer Science Departmentcurrent🎓University of Wisconsin–MadisonMadison · United States2007–2016 · 14 papersEducation 2007–2009 · M.S., Computer Sciences🎓University of Wisconsin SystemMadison · United States2014 · 3 papers
🏛️University of WisconsinMadison · United States2009–2015Education 2009–2015 · PhD, Computer Sciences
🎓Duquesne UniversityPittsburgh · United States2003–2007Education 2003–2007 · B.S., Computer ScienceEducation 2003–2007 · B.A., Mathematics

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 2 worksComputer Science · 2 worksSocial Sciences · 1 workSociology and Political Science · 1 workArts and Humanities · 1 workLanguage and Linguistics · 1 work

🧭 Topics 2Research subjects and languages the work is about.Bias, fairness & safety · 1 workLanguage models & pretraining · 1 work

💡 Concepts 1Key ideas and methods explained on our concept pages.Machine learning · 1 work

 Works by year

2020s

20231 paper

2010s

20171 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting (2017 · 1,036 citations)
    Models trained on sensitive records can expose facts about the people in their training sets. Before this work, the causes of that leakage were explained mostly through scattered anecdotes. Yeom, Giacomelli, Fredrikson and Jha study two black-box threats. Membership inference asks whether a given record was used for…
  2. Universal and Transferable Adversarial Attacks on Aligned Language Models (2023 · 1,005 citations)
    Aligned chat models refuse harmful requests, but earlier jailbreaks were handcrafted and fragile, and automatic prompt search had mostly failed.

All works

4 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

  1. Privacy Risk in Machine Learning: Analyzing the Connection to OverfittingarXiv:1709.01604Samuel Yeom, Irene Giacomelli, Matt Fredrikson, et al.2017 · 1,036 citations
  2. Universal and Transferable Adversarial Attacks on Aligned Language ModelsarXiv:2307.15043Andy Zou, Zifan Wang, Nicholas Carlini, et al.2023 · 1,005 citations
  3. Improving Alignment and Robustness with Circuit Breakers ↗arXiv:2406.04313 · no summary yetAndy Zou et al.2024 · 83 citations
  4. Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration Testing ↗arXiv (Cornell University) · no summary yetJustin W. Lin et al.2025 · 1 citation

 Co-authors here

6 co-authors with a page, the most papers together first.

 Cited by

Papers of our library cite their works 1,295 times (of the 149,439 papers whose bibliographies we read); 272 citing papers with a page here →.

Updated

This page in Markdown → https://md.research.elamur.ai/free/en/authors/matt-fredrikson/