On Episode 157 of the Silver Bullet Security Podcast, BIML’s Gary McGraw hosts Tim Schulz. Tim talks about whitebox control and observability in machine learning systems (and especially transformer architectures), the limits of red teaming for securing AI, “neural surgery,” Agentic AI and the confused deputy problem, and the economics of network “smallification.” #AI #ML #MLsec
https://berryvilleiml.com/2026/06/01/silver-bullet-security-podcast-157-tim-schulz/
What exactly does BIML work on all day? Listen to this podcast and find out. #DataScience #data #MLsec
As a founder of the Berryville Institute of Machine Learning, Gary McGraw has been researching AI security since before most people knew what machine learning was. He's identified 78 risks across ML systems and was sounding the alarm on recursive pollution and model collapse long before those terms went mainstream. He joins Sid and Lee to break down what practitioners need to understand about the systems they're implementing, why 23 of those risks live in a black box controlled entirely by the foundation model vendors, and what good governance looks like when you can't see inside the thing you're governing.
Here come the claws! Agentic #AI for small business may get around to security "later."
#MLsec adjacent
https://www.nytimes.com/2026/06/04/magazine/ai-agents-openclaw-small-business.html
As a founder of the Berryville Institute of Machine Learning, Gary McGraw has been researching AI security since before most people knew what machine learning was. He's identified 78 risks across ML systems and was sounding the alarm on recursive pollution and model collapse long before those terms went mainstream. He joins Sid and Lee to break down what practitioners need to understand about the systems they're implementing, why 23 of those risks live in a black box controlled entirely by the foundation model vendors, and what good governance looks like when you can't see inside the thing you're governing.
I was a guest on the Data Culture podcast
We talked about many aspects of #MLsec including recursive pollution, data curation, What machines and How machines. And #AI governance.
It was fun. Have a listen.
As a founder of the Berryville Institute of Machine Learning, Gary McGraw has been researching AI security since before most people knew what machine learning was. He's identified 78 risks across ML systems and was sounding the alarm on recursive pollution and model collapse long before those terms went mainstream. He joins Sid and Lee to break down what practitioners need to understand about the systems they're implementing, why 23 of those risks live in a black box controlled entirely by the foundation model vendors, and what good governance looks like when you can't see inside the thing you're governing.
@aristot73 BENCHMARKS DO NOT WORK FOR SECURITY #MLsec
Gary McGraw
noplasticshower