AI safety researcher

Aaron Grattafiori

Google Scholar dblp

Evaluation and benchmarks 1Other 1

Latest AI safety papers

On this site: 3 papers

April 2025

WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks
Apr 22Evaluation and benchmarksarXiv ↗

October 2024

Automated Red Teaming with GOAT: the Generative Offensive Agent Tester
Oct 2arXiv ↗

July 2024

The Llama 3 Herd of Models
Jul 31OtherarXiv ↗

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