SEC536: Adversarial AI - Penetration Testing AI Systems


Experience SANS training through course previews.
Learn MoreLet us help.
Contact usBecome a member for instant access to our free resources.
Sign UpWe're here to help.
Contact UsAI supply chains ship unvetted models and datasets because VM tooling can’t see inside them. Risks aren’t just CVEs: dataset poisoning, integrity loss, misuse/misalignment, and license issues. With no NVD for AI artifacts, we operationalize AIBOMs as the missing substrate—structured metadata for provenance, lineage, licensing, and revisions—plus policy-as-code CI/CD gates, PSIRT integration, and offline caching of Hugging Face artifacts.


Dr. Ugur Koc is a Senior AI R&D Engineer at Manifest Cyber, where he leads the design and development of AI Risk Management solutions like AI-BOM generation and automated policy evaluation.
Read more about Ugur Koc