As Large Language Models evolve into autonomous agents capable of executing complex workflows, the attack surface expands exponentially. It is no longer enough to guard against prompt injection; we must now secure the actions the AI takes. This talk introduces a comprehensive framework for securing Agentic AI, moving beyond basic guardrails to architectural resilience.
· Australian Computer Society, NSW Chapter (webinar)
Webinar for the NSW Chapter of the Australian Computer Society on Passkeys — what they are, how they work, and where they fit in modern authentication.