AI Security Summit — October 15, 2026

An intentionally small room. CISOs, VPs of Security, and Heads of AI from the companies actually deploying these systems, working through the strategic problems together: org design for AI security, board-level risk communication, and how to staff teams for threats that didn't exist two years ago. The size is the point — this isn't a keynote audience, it's a working session.

Who Should Attend:

• Leaders driving AI strategy and risk decisions
• C-suite execs (CISOs, CTOs, CIOs, etc.) with AI responsibility
• VPs/Heads of Engineering, AI, Security, Platform, or Infrastructure

Topics we’ll cover:

• What AI risk actually looks like in board meetings — metrics, frameworks, and real questions directors ask
• Practical governance patterns — model approval gates, ownership maps, policy checklists
• Concrete supply chain risk: what to verify in third-party models and where past breaches started
• Where security slows teams vs where it stops costly outages or bad data leaks
• Case reviews of real AI security incidents — attack vectors, fixes applied, and measurable outcomes

This is for people who must justify decisions with evidence — not slogans — and run AI programs at enterprise scale.

Live model exploitation demos, architecture teardowns from teams shipping AI at scale, and the workshops where you actually break things (then fix them). LLM security, AI red teaming, and secure-by-default development — from the people doing it daily.

Who Should Attend:

• Engineers building AI features and infrastructure
• AppSec teams testing those systems
• AI/ML engineers and researchers tuning and deploying models
• Platform/architecture engineers owning pipelines and endpoints
• AI security practitioners responsible for detection and response

Topics we’ll cover:

• Threat modeling for AI/ML with concrete attack patterns and failure cases
• Securing models, training data, pipelines, and inference endpoints — with config examples and code references
• Live red team demos — prompt injection exploits, misuse chains, and model abuse patterns
• LLM security hardening: prompt safety, hallucination controls, and abuse mitigation code snippets
• Detection and monitoring playbooks — what logs matter, thresholds to watch, and incident response steps that have worked in real environments

Expect actual examples, configs, test cases, and clear steps you can use this week — not marketing language.