AI safety researcher

Wenke Lee

Georgia Institute of Technology

Google Scholar dblp OpenReview ORCID Homepage

Last 12 months2 papers

AI safety papers from the last year

On this site: 10 papers

August 2026

ARMOR: Manifold-Oriented Training for Adversarially Robust Aerial Object Detection under Data Scarcity
Aug 30arXiv ↗

July 2026

ALLUDE: A Unified Evaluation System for Configurable Attacks in Differentiable Environments
Jul 19arXiv ↗

Authorship follows dblp and the author's own Google Scholar profile; only AI safety papers on this site are listed.