AI safety researcher

Qinghua Lu

CSIRO

Google Scholar dblp ORCID Homepage

Last 12 months4 papers

Other 1

AI safety papers from the last year

On this site: 17 papers

September 2026

AI Safety: Not Optional, Not Later
Sep 9OtherarXiv ↗

January 2026

A Structured Approach to Safety Case Construction for AI Systems
Jan 30arXiv ↗
Improving Methodologies for LLM Evaluations Across Global Languages
Jan 22arXiv ↗
Improving Methodologies for Agentic Evaluations Across Domains: Leakage of Sensitive Information, Fraud and Cybersecurity Threats
Jan 22arXiv ↗

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