AI safety researcher

Vyas Sekar

Google Scholar dblp

Latest AI safety papers

On this site: 4 papers

January 2025

Incalmo: An Autonomous LLM-assisted System for Red Teaming Multi-Host Networks
Jan 27arXiv ↗

June 2022

On the Privacy Properties of GAN-generated Samples
Jun 3arXiv ↗

November 2019

Enhancing the Privacy of Federated Learning with Sketching
Nov 5arXiv ↗
Privacy for Free: Communication-Efficient Learning with Differential Privacy Using Sketches
Nov 3arXiv ↗

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