Export
The link always opens the latest version of this page.
Ask an AI about it
Open in ChatGPTA new chat that reads this entry from the site Open in ClaudeThe same, in ClaudeShare the link instead of a file, and they will always see the latest version.
Files are a snapshot of today. The live page has anything newer.
JadePuffer
- Type
- ransomware 7 sources
JadePuffer is a ransomware variant characterized by autonomous attack capabilities driven by large language models (LLMs).
Capabilities
JadePuffer executes a fully autonomous intrusion chain from initial access through database extortion, with documented coordination of 600+ payloads 1. The malware employs LLM-driven orchestration to automate multiple attack phases: reconnaissance, credential harvesting, lateral movement, persistence establishment, data encryption, and extortion 2. It performs autonomous reconnaissance and credential discovery to enable lateral movement across compromised networks 3.
The malware implements AI-driven automation of the complete attack lifecycle, including reconnaissance, credential theft, lateral movement, persistence mechanisms, encryption, and resource destruction 4. LLM capabilities support initial access, database compromise, and extortion operations 5.
JadePuffer encrypts data as part of its attack chain and conducts extortion operations. Data destruction capabilities have been observed, though with lower confidence.
Classification
JadePuffer is classified as ransomware based on high-confidence reporting across multiple sources.
Facts 2
| Attribute | Value | Confidence | Sources | Cited |
|---|---|---|---|---|
| Type | ransomware | high | 7 | source ↗ |
| First seen | 2025 disputed
also reported: 2024 (medium)
|
medium | 2 | source ↗ |
Capabilities 8
- data destruction
- AI-driven automation of attack chain including reconnaissance, credential theft, lateral movement, persistence, encryption, and resource destruction
- LLM-driven autonomous attack orchestration, credential harvesting, persistence, lateral movement, data encryption, extortion
- LLM-driven extortion, initial access, database compromise, data destruction
- extortion
- autonomous intrusion chain from initial access to database extortion using LLM; executed 600+ coordinated payloads
- autonomous reconnaissance, credential discovery, lateral movement, data destruction
- encryption
Neighbourhood
Exploits 3
Targets 8
Uses 5
Frequently mentioned together 16
Sources 19
- Ransomware report: VPNs in the crosshairs, AI attacks · CSO Online
- Smooth AI criminal drives 'first' end-to-end agentic ransomware attack · The Register: Security
- AI Raises the Stakes for Mexico’s Cyber Defenses - Mexico Business News · Google News: Cyber Security
- JadePuffer agentic AI attacks target Azure, destroy cloud resources · BleepingComputer
- JadePuffer crims hijacked Azure identities and used them to blow up cloud resources · The Register: Security
5 of 19 sources shown · Pro unlocks the full list