Navigating AI security Identifying risks & implementing mitigations with Simran Kaur

How do you keep AI‑powered systems from turning today’s innovation into tomorrow’s breach, outage, or headline‑grabbing incident? In this talk, Simran Kaur, a Security Assurance Engineer at Microsoft with 15+ years in IT and 8+ years in cybersecurity, walks through real‑world AI security risks and practical mitigation strategies for organizations building or consuming AI solutions. You’ll hear how familiar issues like identity compromise, data exposure, and supply chain attacks evolve in an AI context, and why concepts like responsible AI, zero trust, and shared responsibility are non‑negotiable when deploying modern AI workloads. This session is ideal for blue teams, security architects, cloud and platform engineers, AppSec practitioners, and technology leaders who need to understand threats like hallucination, prompt injection (direct and indirect), RAG and embedding risks, and excessive agency in agentic AI systems. Key questions explored include: What can go wrong when AI systems