Where should a security control live in an agentic system, and what should happen when it fails?
The InfoQ Certified AI Security & Privacy Engineering Program works through it.
Review the program and syllabus: https://certification.qconferences.com/ai-security-privacy?utm_source=infoq-mastodon&utm_medium=social&utm_campaign=post-sep30-infoqcert&utm_content=ai-security-october
Comments (2)
Sign in to comment
The capstone is a security and privacy assessment for an AI product architecture, covering risks, controls, tests and ownership.
Facilitated by Katharine Jarmul, author of Practical Data Privacy.
Next cohort: October 26.
Across five weeks, participants trace sensitive-data flows, threat model and red team an AI workflow, work through guardrails and sandboxing, and test controls with observability and evals.