In this interview David and Dr Mike Pound discuss Agentic AI and how powerful it is powerful, but prompt injection and untrusted PDFs can leak data or alter records. Learn least privilege, input and output filtering, and model trust risks.
// Sponsored SEGMENT //
Big thank you to Proton Pass for sponsoring this video. To sign up for Proton Pass, please use the following link https://proton.me/davidbombal to get a 40% discount
// Mike SOCIAL //
X: https://twitter.com/_mikepound
// David's SOCIAL //
Discord: https://discord.com/invite/usKSyzb
X: https://www.twitter.com/davidbombal
Instagram: https://www.instagram.com/davidbombal
LinkedIn: https://www.linkedin.com/in/davidbombal
Facebook: https://www.facebook.com/davidbombal.co
TikTok: http://tiktok.com/@davidbombal
YouTube: https://www.youtube.com/@davidbombal
Spotify: https://open.spotify.com/show/3f6k6gERfuriI96efWWLQQ
SoundCloud: https://soundcloud.com/davidbombal
Apple Podcast: https://podcasts.apple.com/us/podcast/david-bombal/id1466865532
// MY STUFF //
https://www.amazon.com/shop/davidbombal
// SPONSORS //
Interested in sponsoring my videos? Reach out to my team here: sponsors@davidbombal.com
// MENU //
0:00 - Coming up
0:56 - Proton Pass sponsored segment
02:15 - AI & cybersecurity // Vulnerabilities of AI
12:56 - Direct & Indirect Prompt Injection explained
17:52 - Input & Output Filtering explained
20:20 - AI having access to private data
25:24 - Reactions to AI & cybersecurity
27:06 - Risks of downloading open-source AI models
36:02 - The good and bad of AI models
40:23 - Conclusion
Please note that links listed may be affiliate links and provide me with a small percentage/kickback should you use them to purchase any of the items listed or recommended. Thank you for supporting me and this channel!
Disclaimer: This video is for educational purposes only.
#cybersecurity #ai #promptinjection