Metraipolis › archive › dc_e32b4934fd60
OllamaDrama: Designing and Deploying a Honeypot to Measure Attacks on Exposed LLM Infrastructure — arXiv:2609.29757
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.29757
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T04:53:25.169Z
- SHA-256 of the archived text
189a633c8f1e69bb069b4a652297b95ac9432293b800f084e703f804ce6a6bd3- Stable URL of this page
https://metraipolis.com/documento/dc_e32b4934fd60
How to cite
OllamaDrama: Designing and Deploying a Honeypot to Measure Attacks on Exposed LLM Infrastructure — arXiv:2609.29757 — arXiv (en), https://arxiv.org/abs/2609.29757 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e32b4934fd60 (Metraipolis archive dc_e32b4934fd60, sha256 189a633c8f1e69bb069b4a652297b95ac9432293b800f084e703f804ce6a6bd3)
BibTeX
@misc{dce32b4934fd60,
title = {OllamaDrama: Designing and Deploying a Honeypot to Measure Attacks on Exposed LLM Infrastructure — arXiv:2609.29757},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.29757},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e32b4934fd60; sha256 189a633c8f1e69bb069b4a652297b95ac9432293b800f084e703f804ce6a6bd3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29757. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Publicly exposed large language model (LLM) infrastructure creates a growing attack surface, yet real-world targeting remains poorly understood. We present Ollure, a low- and medium-interaction honeypot that emulates the Ollama API without a backend LLM. Spanning four deployments across cloud and university networks, Ollure operated for 84 days and recorded 290,887 interactions from 2,793 unique source IP addresses. Most of the activity consisted of automated discovery, fingerprinting, and model enumeration. However, we also observed concrete exploitation attempts against both the infrastructure and LLM layers. These included model management abuse, path traversal and SSRF probes, RCE and cryptocurrency mining payloads, resource exhaustion attempts, prompt injection, information extraction, and agent-oriented tool use. Our results provide empirical insight into real-world threats against exposed, self-hosted LLM services. Tema degli esploratori: fiducia digitale e crittografia (retro-catalogo arXiv: annunci del 2026-09-25 in cs.CR). Categorie arXiv: Cryptography and Security (cs.CR). Pagina del lavoro: https://arxiv.org/abs/2609.29757 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T04:30:43.838Z dalla pagina https://arxiv.org/catchup/cs.CR/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).