All people

Researcher

Xuandong Zhao

XZ

Member of Technical Staff at OpenAI

Zhao studies how frontier language models and AI agents can become more reliable while protecting privacy and resisting misuse. His research covers model provenance, safety evaluations and attacks that reveal where proposed safeguards fail. He joined OpenAI in July 2026 after research at Berkeley.

See something inaccurate or outdated?

Background

Current role
Member of Technical Staff Jun 2026-present
Previously
Jun 2024-Jun 2026Postdoctoral Researcher,
Jun 2023-Sep 2023Research Intern,
About this data

Work and education history is primarily focused on AI-relevant roles and may not be comprehensive.

Last editorial review: August 8, 2026

News 1

Citation Trend

1 snapshots
Citation snapshot on Jul 3, '265,084Jul 3, '26
5,084citations as of Jul 3, '26
For today’s citation count and citations per paper, visit Google Scholar.
Xuandong Zhao: Researcher profile · Turing Tree