175,000 Ollama AI Servers Found Publicly Exposed Worldwide, Enabling Malicious Activities
By
heresie-dabord
Pure flour-power. Hearty enough to carry you through lunch.
Summary
Security researchers from SentinelOne and Censys have discovered approximately 175,000 publicly exposed Ollama AI servers worldwide that are misconfigured to listen to the internet instead of only locally. These exposed systems are being actively abused for malicious activities including LLMjacking (stealing AI model access), creating malicious content, and being sold on black markets. The article warns organizations running Ollama instances to reconfigure their systems immediately to prevent security breaches.
Key quotes
· 4 pulledSecurity researchers have claimed around 175,000 Ollama systems worldwide are exposed, putting them at risk of all sorts of malicious activities.
Recently, SentinelOne SentinelLABS and Censys discovered many businesses are running AI models locally (the AI listens only to the computer it's running on, not the internet) using Ollama.
However, in around 175,000 cases, these are misconfigured to listen
Exposed servers are being used for LLMjacking, creating malicious content and being sold on the black market.
You might also wanna read
Google reports first evidence of hackers using AI to develop zero-day security exploit
Google has reported evidence of hackers using AI to develop a zero-day security vulnerability, marking the first time the company has observ
politico.com·10h ago
How hackers exploit AI chatbot personalities through prompt injection attacks
This article discusses how hackers are exploiting AI chatbot "personalities" through prompt injection and jailbreaking techniques. Initially
The Verge·7d ago
Google Confirms First Known Case of Hackers Using AI to Discover Software Vulnerability
Google's security researchers have identified the first known instance of criminal hackers using artificial intelligence to discover a previ
nytimes.com·20d ago
Why Anthropic's Mythos AI model is actually a breakthrough for cybersecurity defense
The article argues that Anthropic's Mythos AI model, despite being portrayed as a dangerous cybersecurity threat by the company and media, i
sfstandard.com·25d ago
AI bug-finding systems uncover real vulnerabilities at DARPA cybersecurity challenge
The article discusses the DARPA AI Cyber Challenge (AIxCC) held in Las Vegas, where top cybersecurity teams demonstrated AI-powered bug-find
The Verge·1mo ago
Anthropic Investigates Unauthorized Access to Claude Mythos Preview AI System
Anthropic is investigating unauthorized access to its Claude Mythos Preview AI system through a third-party vendor environment. The breach i
mythoswatch.org·1mo ago