Stanford University · Course
AI Security (XACS134)
AI Security (XACS134) is a short self-paced Stanford Online course on the security challenges of modern AI systems: how vulnerabilities enter through design, training and deployment, and the attacks that exploit foundation models, retrieval systems and agents.
Who it suits
- Security and software professionals who build or defend AI systems.
- Practitioners who want CPE credit toward (ISC)² certifications.
What it covers
- Attacks such as prompt injection, adversarial inputs, data poisoning and model extraction.
- Common AI misapplications and the risks of multi-agent collaboration.
- Emerging defences: secure architectures, verifiable training and prompt-level protections.
- Real-world breaches and hands-on exercises.
Common questions about AI Security (XACS134)
- How long is access?
- Stanford lists 60 days of course access, 1 CEU-equivalent and a Record of Completion.
- Is there CPE credit?
- Stanford says you can qualify for Group A or Group B CPE credits for (ISC)² certifications such as the CISSP, with final approval by (ISC)².
- Which programme is it in?
- Stanford lists it in its Advanced Cybersecurity Program.
More like this
Keep learning on Infrato
- Path: AI for software developers
- More from Stanford University: all Stanford University listings in the directory
- Explore all AI courses
Where this comes from
Written from Stanford University’s own pages, read on 2026-10-14. Content, prices and availability change, so the provider’s page is the source. We are not affiliated with Stanford University and this is not an endorsement.