EP150 Taming the AI Beast: Threat Modeling for Modern AI Systems with Gary McGraw

[chuvakin]

Guest:

• Dr Gary McGraw, founder of the Berryville Institute of Machine Learning

Subscribe at Google Podcasts.

Subscribe at Spotify.

Subscribe at Apple Podcasts.

Subscribe at YouTube

Topics covered:

• Gary, you’ve been doing software security for many decades, so tell us: are we really behind on securing ML and AI systems? 
• If not SBOM for data or “DBOM”, then what? Can data supply chain tools or just better data governance practices help?
• How would you threat model a system with ML in it or a new ML system you are building? 
• What are the key differences and similarities between securing AI and securing a traditional, complex enterprise system?
• What are the key differences between securing the AI you built and AI you buy or subscribe to?
• Which security tools and frameworks will solve all of these problems for us? 

Resources:

• EP135 AI and Security: The Good, the Bad, and the Magical
• Gary McGraw books
• “An Architectural Risk Analysis Of Machine Learning Systems: Toward More Secure Machine Learning“ paper
• “What to think about when you’re thinking about securing AI”
• Annotated ML Security bibliography
• Tay bot story (2016)
• “Can you melt eggs?”
• “Microsoft AI researchers accidentally leak 38TB of company data”
• “Random number generator attack”
• “Google's AI Red Team: the ethical hackers making AI safer”
• Introducing Google’s Secure AI Framework

Do you have something cool to share? Some questions? Let us know:

• Web cloud.withgoogle.com/cloudsecurity/podcast
• Mail cloudsecuritypodcast@google.com
• Twitter@CloudSecPodcast