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 Us
Allen Westley is a senior cybersecurity leader and practitioner with over 20 years of experience securing high-risk environments where failure carries real consequences. His work sits at the intersection of AI-enabled systems, human decision integrity, and national-security-grade risk management—focused on what breaks when autonomy, speed, and trust collide.
Allen currently leads cyber intelligence efforts across classified systems in the Defense Industrial Base, where he works directly with security engineering, incident response, and governance teams navigating the rapid introduction of AI into operational workflows. His day-to-day work includes assessing agentic tool use, shadow AI adoption, and the silent erosion of human judgment in environments where AI outputs increasingly influence decisions without explicit delegation.
Rather than treating AI risk as a model-centric problem, Allen’s work examines cognitive failure modes as a control gap and how over-reliance, confidence inflation, and decision off-loading create exploitable conditions that traditional technical controls fail to detect. He has developed practical methods for identifying and instrumenting these failure signals, referred to as Cognitive Indicators of Compromise (C-IOCs), informed by observed behavior in live environments and red-team-inspired testing.
Allen is a frequent contributor to industry discussions on AI security, governance, and operational risk, with a focus on separating deployed reality from aspirational frameworks. He brings a practitioner’s perspective shaped by hands-on implementation, governance friction, and the uncomfortable lessons learned when controls meet production systems.
Speaker / Contributor: This individual participates in SANS events, presentations, written content, or other community resources as an external contributor. They are not a SANS employee, instructor, or affiliate.
Review relevant educational resources made with contribution from this instructor.