Microsoft Copilot Studio

Dr. Janet Bastiman has been making convincing deepfakes since 2017, long before most people knew the word. Now the Chief Data Scientist at Napier AI, she joins Mo to get into why fraud is actually easier to catch than money laundering, how a deepfake already talked a finance team out of millions, and why the human analysts checking AI matter more than ever.

As AI systems gain autonomy, organizations need security approaches built specifically for AI behavior. Learn why AI-driven red teaming is becoming a critical defense layer.

This report evaluates default and opt-in content protections under real-world and adversarial conditions. The study examines safeguard effectiveness, resilience against attempts to surface inappropriate content, and platform improvements made following testing.