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 UsIndustrial environments are not being compromised by deployed AI models, but by uncontrolled AI use by engineers, analysts, and vendors interacting with OT data. This session presents a real world case study where shadow AI introduced new risks to safety, availability, and integrity in an ICS adjacent environment. Attendees will learn how AI bypassed segmentation and existing OT controls through human workflows, why traditional ICS defenses failed to detect it, and how the SANS ICS 5 Critical Controls were applied to restore visibility and reduce risk. The session concludes with concrete steps to identify AI touching OT systems, assess operational impact, and implement controls that improve resilience without disrupting operations.


Teri Green is an award winning cybersecurity and technology leader specializing in AI security, governance, and operational risk in production environments. Her work focuses on how autonomous and generative AI systems reshape enterprise attack surfaces, and how organizations can defend, govern, and deploy AI responsibly without slowing innovation or eroding trust.
Read more about Teri Green







