In the world of Generative AI, natural language has become the new executable. Attackers no longer need complex code to breach your systems, sometimes, asking for a "poem" is enough to steal your passwords .
In this episode, Eduardo Garcia (Global Head of Cloud Security Architecture at Check Point) joins Ashish to explain the paradigm shift in AI security. He shares his experience building AI-powered fraud detection systems and why traditional security controls fail against intent-based attacks like prompt injection and data poisoning .
We dive deep into the reality of Shadow AI, where employees unknowingly train public models with sensitive corporate data , and the sophisticated world of Deepfakes, where attackers can bypass biometric security using AI-generated images unless you're tracking micro-movements of the eye .
Guest Socials - Eduardo's Linkedin
Podcast Twitter - @CloudSecPod
If you want to watch videos of this LIVE STREAMED episode and past episodes - Check out our other Cloud Security Social Channels:
If you are interested in AI Security
, you can check out our sister podcast - AI Security Podcast
(00:00) Introduction(01:55) Who is Eduardo Garcia? (Check Point)(03:00) Defining Security for GenAI: The Focus on Prompts (05:20) Why Natural Language is the New Executable (08:50) Multilingual Attacks: Bypassing Filters with Mandarin (12:00) Shift Left vs. Shift Right: The 70/30 Rule for AI Security (15:30) The "Poem Hack": Stealing Passwords with Creative Prompts (21:00) Shadow AI: The "HR Spreadsheet" Leak Scenario (25:40) Security vs. Compliance in a Blurring World (28:00) The Conflict: "My Budget Doesn't Include Security" (34:00) The 5 V's of AI Data: Volume, Veracity, Velocity (40:00) Deepfakes & Biometrics: Detecting Micro-Movements (43:40) Fun Questions: Soccer, Family, and Honduran Tacos