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
Viswanath “Vis” Chirravuri brings more than 20 years of cybersecurity and product security experience to the fast-moving intersection of AI security, application security, DevSecOps, and software supply chain security. A SANS Certified Instructor Candidate for SEC545: GenAI and LLM Application Security and the author of SEC546: Securing Agentic AI, and Chief AI Security Governance at Thales Cyber and Digital, he helps students connect GenAI and LLM application security to the realities of product security, secure software development, cloud security, and AI/ML lifecycle governance.
Vis holds a Master of Science in Information Security Engineering from the SANS Technology Institute and is pursuing a Doctor of Engineering in Cybersecurity Analytics at The George Washington University. He holds more than 35 industry certifications, including Certified Information Systems Security Professional, Project Management Professional, 23 GIAC certifications including GIAC Security Expert. He is also a CompTIA Subject Matter Expert, a GIAC Advisory Board member, founder of AI AppSec Academy, and a contributor to open security resources including the Thales Secure Machine Learning Framework.
Vis approaches cybersecurity as both a technical discipline and a mentoring practice. He has trained thousands of software developers globally in secure architecture, design, and coding practices; speaks at conferences including RSA Conference and OWASP; and leads security education efforts around AI, AppSec, and DevSecOps.. Outside work, he stays active through sports, teaches yoga, explores vegetarian cooking, and spends time with his family.
Here are upcoming opportunities to train with this expert instructor.
Explore content featuring this instructor’s insights and expertise.
Attendees will walk away with a clear mental model of where AI accelerates AppSec, where AI must be defended, and how to adopt vendor AI responsibly, all supported by open-source frameworks and ready to use resources.

Agentic AI doesn’t just answer, it acts. This session will give leaders and defenders a starting point to enable agents safely, combining policy, culture, and technical controls like gateways, guardrails, sandboxing, and runtime governance.

This webcast explores the evolution of machine learning context-based prompting, RAG, Agentic AI, and fine-tuning and associated risks.
