))
Ep. 46: Securing AI: Misbehavior Even the Experts Couldn't Predict
Manage episode 455973506 series 3467081
Content provided by Joe Patti and Adam Roth, Joe Patti, and Adam Roth. All podcast content including episodes, graphics, and podcast descriptions are uploaded and provided directly by Joe Patti and Adam Roth, Joe Patti, and Adam Roth or their podcast platform partner. If you believe someone is using your copyrighted work without your permission, you can follow the process outlined here https://ro.player.fm/legal.
Artificial intelligence is revolutionizing industries, and cybersecurity experts are navigating uncharted territory to keep pace. In this episode of the Security Cocktail Hour podcast, Alec Crawford, Founder and CEO of AI Risk, Inc., joins co-hosts Joe Patti and Adam Roth for a dive into the practical, technical, and ethical challenges of AI - including some surprises nobody saw coming, as well as what an adversary can do with a drone. From early work with neural networks to cutting edge large language models, Alec shares the challenges he's taking on to secure today’s generative AI models.
Highlights include:
🔒 Vulnerabilities AI introduces to corporate environments
🔒 Creative and unexpected ways hackers are manipulating AI systems
🔒 Why regulating AI is so challenging—and what might work better
For more insights from Alec, tune into his podcast, AI Risk-Reward or visit AI Risk, Inc..
#InformationSecurity #Infosec #Cybersecurity #Podcast #ArtificialIntelligence #AI #GenAI #GenerativeAI #Hacking #TechInnovation #Regulation #TechRegulation #Drone
49 episoade
Distribuie
