In this episode of Threat Vector, host David Moulton, Director of Thought Leadership for Unit 42, speaks with Spencer Thellmann, Principal Product Manager at Palo Alto Networks. Spencer brings a background in AI policy from the University of Cambridge and now leads development of real-time AI runtime security solutions. Together, they explore the dual challenges of securing employee use of generative AI tools and defending internally built AI models and agents.

Topics include prompt injection, model scanning, red teaming, agent posture control, and how AI changes cloud security architecture. Listeners will take away key mental models and practical guidance for building resilient, trustworthy AI systems.

Explore More on AI Security and Strategy

• Defending in the AI Era: Learn how to protect your enterprise from the new threat landscape shaped by AI.
• Cybersecurity Perspectives Magazine: Stay ahead of the trends reshaping enterprise defense, including AI, cloud, and workforce security.
• Unit 42 Threat Frontier: Explore cutting-edge threat intelligence and research from Unit 42.

Want more Threat Vector?

• Securing AI in the Enterprise with Tanya Shastri and Navneet Singh explores how to architect AI securely from the start.
• Enhancing Ethical Hacking with AI with Ryan Barger dives into offensive applications of AI in red teaming.

Join the conversation on our social media channels:

• Website: ⁠⁠⁠⁠https://www.paloaltonetworks.com/
• Threat Research: ⁠⁠⁠⁠https://unit42.paloaltonetworks.com/⁠⁠⁠⁠
• Facebook: ⁠⁠⁠⁠https://www.facebook.com/LifeatPaloAltoNetworks/⁠⁠⁠⁠
• LinkedIn: ⁠⁠⁠⁠https://www.linkedin.com/company/unit42/⁠⁠⁠⁠
• YouTube: @paloaltonetworks
• Twitter: ⁠⁠⁠⁠https://twitter.com/PaloAltoNtwks⁠⁠⁠⁠