#
DIFF.BLOG
New
Following
Discover
Jobs
More
Top Writers
Suggest a blog
Upvotes plugin
Report bug
Contact
About
Sign up
The home for great developer writing.
We surface the best developer writing from thousands of independent blogs, updated daily.
Join Diff.blog
TOPICS
security: Enhancing AI security through global AI red teaming
1
·
Sujith Quintelier
·
July 28, 2026, 3:33 a.m.
AI Security
red teaming
Microsoft Security
AI Risks
Summary
Microsoft has launched the External Red Team Alliance (EXTRA), an initiative aimed at enhancing AI security through collaboration with experts and researchers. The focus is on identifying AI risks and improving security for frontier AI systems.
Read full post on quintelier.dev →
MORE POSTS LIKE THIS
MiDojo: Improve AI agent security with real-world red-teaming
Red Hat ·
Aug 10, 2026
AI Security
red teaming
security: Advance Zero Trust for AI: New tools and guidance to secure AI agents and DevSecOps
Sujith Quintelier ·
Aug 5, 2026
zero-trust
AI Security
Breaking the Black Box: A Case Study in Red-Teaming a Government Education AI
Sentinelone ·
May 18, 2026
Company
black box
How I Think About Agentic Risks
Gianluca Brindisi ·
Dec 21, 2025
AI Risks
Mental Models
Deepening our partnership with the UK AI Security Institute
DeepMind ·
Dec 11, 2025
ai-safety
AI Security
How AI Builders Will Get Hacked
Daniel Miessler ·
Aug 17, 2026
AI Security
development tools
Discover more posts →
AUTHOR
RECENT POSTS FROM THE AUTHOR
Choose how you want to continue.
Continue with GitHub
Continue with Google