All people
Mary Phuong portrait

Researcher

Mary Phuong

Research Scientist at Google DeepMind

Mary Phuong is a Google DeepMind safety researcher working on AI control: ways to secure systems even if an AI tries to bypass safeguards. She co-authored early evaluations of dangerous capabilities in frontier models and the GDM AI Control Roadmap, which proposes layered defenses for agents deployed inside AI labs.

Career & education

Current role
Mar 2022-present
Research Scientist

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

Citation Trend

Total citations to scholarly work, including research papers, technical reports, books and theses, as recorded by Google Scholar. Each point is a dated snapshot.
1 snapshots
Citation snapshot on Sep 30, '2623,420Sep 30, '26
citations23,420As of Sep 30, '26
For today’s citation count and per work, visit Google Scholar.

Updates 1

person_addedDeepMind safety researcher Mary Phuong added

Phuong works on AI control and frontier-model evaluations at Google DeepMind, including the GDM AI Control Roadmap.

September 30, 2026
About this profile

Based on public sources. If accuracy is important, verify details using the links or references.

For corrections, updates, or requests to remove information, contact us.

Reviewed September 30, 2026 · Checked for accuracy and new information.

Sharing card

Related people