Problem
Research questions and friction points this paper is trying to address.
self-hosted large language model
public Internet
exposed Ollama endpoints
structural exposure surface
insecure deployment practices
Ollama in the Wild: A Longitudinal Measurement of Exposed Ollama LLM Endpoints at Internet Scale
🤖 AI Summary
研究通过365天的测量分析了公开互联网上Ollama LLM端点的暴露情况，揭示了其持久性、增长性和集中性，并指出存在不安全部署的问题。
📝 Abstract
Self-hosted large language model (LLM) serving is emerging as a distinct category of Internet service, but we still know little about how these deployments appear and change on the public Internet. We present a 365-day longitudinal measurement of exposed Ollama endpoints (port 11434) from February 2025 to February 2026, combining daily active probing with GeoIP/ASN enrichment, PTR and port-443 host observations, and survival analysis. Across 362 observation days and approximately 4.8 million IP$\times$day observations, 26.4% of the 152,137 cumulative IPs appear for a single day; across five selected CVEs, only 0.43-2.90% of below-fix IPs upgraded in place; the top five countries/regions account for over 70% of weighted observations; and cloud and hosting providers dominate the top ASNs. These results characterize exposed Ollama as a structural exposure surface: persistent, growing, and heavily concentrated. At the same time, old versions, common model choices, cloud and hosting ASNs, PTR categories, and TLS certificate patterns remain visible across the year, indicating recurring insecure deployment practices in cloud infrastructure and the potential reach of provider-level mitigation.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Longitudinal Measurement
Ollama LLM Endpoints
Internet Scale
Survival Analysis
Insecure Deployment Practices
🔎 Similar Papers
2024-03-31Citations: 6
