AI safety researcher

Emilio Ferrara

University of Southern California

Google Scholar dblp ORCID Homepage

Last 12 months8 papers

Evaluation and benchmarks 1

AI safety papers from the last year

On this site: 25 papers

October 2026

Agent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM Systems
Oct 21Evaluation and benchmarksarXiv ↗
Social bot detection in the age of ChatGPT: Challenges and opportunities
Oct 1arXiv ↗

September 2026

Coding Agents with Harness for Safe Robot Control
Sep 17arXiv ↗

May 2026

How Far Will They Go? Red-Teaming Online Influence with Large Language Models
May 20arXiv ↗

January 2026

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