aiqbench takeAI Safety

The article details a specific ransomware campaign targeting AI infrastructure by exploiting authentication flaws in Langflow to encrypt models and training data. This represents a critical shift where attackers now aim directly at the intellectual property within AI systems rather than just general server files. For the community, this underscores the urgent need for robust access controls on code-validation endpoints used in ML development pipelines.

Source coveringCybersecurity News

What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

Agentic JADEPUFFER Exploits Langflow Flaw to Deploy ENCFORGE AI Ransomware

Cybersecurity NewsJuly 21, 20264 min read

A ransomware campaign is now targeting the assets behind artificial intelligence systems. The threat actor known as JADEPUFFER has evolved from damaging databases to deploying ENCFORGE, a ransomware strain designed to encrypt AI models, training data, and vector databases. The operation begins by exploiting CVE-2025-3248, a critical missing-authentication flaw in Langflow’s code-validation endpoint. The bug […] The post Agentic JADEPUFFER Exploits Langflow Flaw to Deploy ENCFORGE AI Ransomware appeared first on Cyber Security News.

A ransomware campaign is now targeting the assets behind artificial intelligence systems. The threat actor known as JADEPUFFER has evolved from damaging databases to deploying ENCFORGE, a ransomware strain designed to encrypt AI models, training data, and vector databases. The operation begins by exploiting CVE-2025-3248, a critical missing-authentication flaw in Langflow’s code-validation endpoint. The bug allows an unauthenticated attacker to run Python code on exposed servers, creating a direct path into environments…

Excerpt shown under the publisher's RSS terms · 72 words · full text and figures are on the publisher's site

Read at Cybersecurity News ↗Ask about this article