Aounon Kumar

2 papers on this site · 2023

current affiliationHarvard University, Cambridge, United States; Samsung (South Korea), Seoul, South Korea; Samsung (United States), Ridgefield Park, United States; Samsung Electronics (South Korea), Seoul, South Korea

Aounon Kumar has 2 papers on this site, in 2023, most of them on Language models & pretraining, Bias, fairness & safety; often with Soheil Feizi.

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

Affiliations

Harvard University · Cambridge, United States — current · 2023–2026 on 6 papers
Samsung (South Korea) · Seoul, South Korea — current · 2026 on 2 papers
Samsung Electronics (South Korea) · Seoul, South Korea — current · 2026 on 2 papers
Samsung (United States) · Ridgefield Park, United States — current · 2026 on 1 paper
University of Maryland, College Park · College Park, United States — 2016–2022 on 10 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

The most cited first (OpenAlex and our library).

Can AI-Generated Text be Reliably Detected? (2023 · 301 citations)
The paper tests whether current detectors of machine-written text still work when someone deliberately tries to fool them.
Certifying LLM Safety against Adversarial Prompting (2023 · 110 citations)
Safety-aligned LLMs can still be jailbroken when an attacker attaches crafted adversarial tokens to a harmful request.

1 more work of theirs is in our library without a page here yet; it will appear as we publish them.

1 co-author with a page, the most papers together first.

Papers of our library cite their works 228 times (of the 140 884 papers whose bibliographies we read); 20 citing papers with a page here →.