State of Cybercrime:
The Hugging Face Breach
Out of the sandbox and into the fire.
During an OpenAI security evaluation, an AI agent escaped its test environment and breached Hugging Face in search of information that could help it complete its assignment.
No attacker. No malicious instructions. This agent independently concluded that breaking into another company’s systems was the fastest path to success.
Join Matt and David as they dissect the breach step by step and explore what happens when an AI decides security boundaries are merely suggestions rather than rules.
Join over 2,000 security pros & get the latest cybercrime news!
Your seat is saved!
About the series
In today's digital landscape, no industry is safe from cybercrime. Hackers continue to exploit vulnerabilities across sectors, leading to highly destructive breaches.
Our State of Cybercrime series sheds light on the latest high-profile attacks while providing actionable insights across every industry.
This episode's segments include...
- Is there any good news?
- AI Vey — because we can't not talk about AI
- The latest Vulnerable Vulnerabilities
- The Highway to the Danger Zone — vulnerabilities you should be patching this week
- Live Q&A
Show hosts:
Matt Radolec
Field CTO, Varonis
David Gibson
Senior VP of Strategic Programs, Varonis
Episode 47
Episode 46
Episode 44