
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.
Want to join us live? Save a seat here: https://www.varonis.com/state-of-cybercrime
More from Varonis ⬇️
Visit our website: https://www.varonis.com
LinkedIn: https://www.linkedin.com/company/varonis
X/Twitter: https://twitter.com/varonis
Instagram: https://www.instagram.com/varonislife/
Flere episoder fra "State of Cybercrime"



Gå ikke glip af nogen episoder af “State of Cybercrime” - abonnér på podcasten med gratisapp GetPodcast.








