JADEPUFFER Evolves: The Agentic Threat Actor Deploys Ransomware Built to Destroy AI Models
Sysdig, Monday, July 20th, 2026
Sysdig tracks JADEPUFFER deploying ransomware designed to destroy trained AI models.
The Sysdig Threat Research Team reports that JADEPUFFER, an agentic threat actor it previously documented, is now using ransomware to destroy trained AI models.
The analysis tracks how the actor evolved its tactics to specifically target and wipe machine learning models as part of extortion operations.
It highlights the growing risk to AI assets as a new extortion lever. The report details the actor's agentic techniques.