State of Cybercrime
Join us for State of Cybercrime, where experts discuss the latest trends and developments in the world of cybercrime and provide insights into how organizations can protect themselves from potential threats.Sponsored by Varonis
- Indexed episodes, last 90 days
- 2
- Latest publication
- Aug 15, 2026
- Audience
- Checking…
- Earliest in this view
- Jul 18, 2026
Latest episodes
The Hugging Face Breach (opens the original)
Read excerpt
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
The Ransomware That Ran Itself (opens the original)
Read excerpt
A complete attack chain run by an AI agent – with zero human hands on the keyboard. JadePuffer is the first AI-driven threat actor to execute a ransomware attack end-to-end – autonomously prioritizing targets, adapting in real time to exploit vulnerabilities, and harvesting sensitive data for extortion. Join Matt and David as they break down what made this attack possible – and why JadePuffer pushes independent AI threat actors from science fiction into real-world operation. Plus: In our Voices
Publishing over time
Last 90 days. Choose a month to open its work.
Recurring subjects
Named in the text we hold. One piece can cover several.
Audience
No verified audience measurement yet.
About this data
Counts cover the work we have indexed. Tone needs enough text and a confident classification. Excerpts and episode notes are not full articles or transcripts.
Identity or attribution wrong? Suggest a correction.