AI coding assistants are rapidly changing how software is built, but their security impact cannot be understood from a single generated response. Development is iterative: developers ask AI to add features, fix bugs, refactor code, and change configurations, creating opportunities for security controls to weaken or disappear.

This talk introduces **security drift**: the gradual introduction, reintroduction, or amplification of vulnerabilities across successive rounds of AI-assisted development. Using experimental examples, I will show how weaknesses involving authentication, input validation, injection, secrets, and insecure configurations evolve as AI repeatedly modifies the same application. Attendees will learn how to measure security drift, identify security regressions, preserve security requirements across prompts, and integrate practical safeguards into AI-assisted development workflows.