#608: Before You Deploy AI Agents, Understand These Attacks

Big thanks to Proton VPN for sponsoring this video. You can use my link: https://protonvpn.com/davidbombal to get 70% off your Proton VPN subscription How do you hack an AI system? And what happens when one malicious instruction spreads between AI agents? I’m joined by Harriet, author of Practical AI Security, to explore how AI models and agents can be manipulated, with practical Python demonstrations. You'll see an image classifier misidentify a rifle, a demonstration of prompt injection spreading across five agents, and how memory poisoning can plant instructions that affect an agent later. We discuss why securing AI takes more than blocking prompt injection, how machine learning creates different security challenges, and what you need to understand before deploying agents in your organisation. Want to learn this yourself? Harriet explains how to get started with her collection of 30+ free Python notebooks, including examples you can explore in Google Colab. We also discuss the skills involved in AI security and how people from different backgrounds can contribute. Topics include: • Adversarial machine learning and image manipulation • Prompt injection and attacks spreading between agents • Memory poisoning and model backdoors • AI supply chain security • Learning AI security with Python • AI security careers, training and fundamentals // Link to No Starch Website for Harriet Farlow’s Book // Order Practical AI Security on No Starch: https://nostarch.com/practical-ai-sec... Use Coupon code FARLOW25 for 25% off Practical AI Security // HarrietHacks Labs REFERENCE // https://labs.harriethacks.com/ // Harriet Farlow’s AI Security Fundamentals Course REFERENCE // https://aisecurityfundamentals.com/ // Harriet Farlow’s SOCIALS // Website: https://harriethacks.com/about/ LinkedIn: / harriet-farlow-654963b7 Instagram: / harriethacks // David's SOCIAL // Discord: discord.com/invite/usKSyzb Twitter: www.twitter.com/davidbombal Instagram: www.instagram.com/davidbombal LinkedIn: www.linkedin.com/in/davidbombal Facebook: www.facebook.com/davidbombal.co TikTok: tiktok.com/@davidbombal YouTube: / @davidbombal Spotify: open.spotify.com/show/3f6k6gE... SoundCloud: / davidbombal Apple Podcast: podcasts.apple.com/us/podcast... // 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 - Intro 01:05 - Harriet Farlow AI security background 05:55 - Proton VPN sponsor segment 08:02 - Practical AI Security book // AI Security 10:40 - Who's the book for 11:32 - Harriet's YouTube channel 12:32 - AI security course 14:27 - Practical demos 15:41 - Hacking an AI demo // Learning how AIs work 22:22 - Hacking an AI summary 24:40 - Hacking an AI visualizations 28:48 - AI deceiving another AI 33:09 - Hacking an AI visualizations continued 34:07 - Rushing to the AI market 36:26 - Adversarial patch explained 38:12 - Vibe coded visuals 40:27 - More visualization 44:04 - Growth of interest in AI security 45:09 - No advanced skills required 49:40 - Get in contact with Harriet Farlow // 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. #aisecurity #aiagents #defcon