LLM-SSHH: An LLM-Powered SSH Honeypot Framework via State Snapshot
Applied System Innovation · 18.05.2026 · 9 (5) · 101
DOI: 10.3390/asi9050101 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied System Innovation, online erschienen am 18.05.2026. Verfasst von Xiang Li und 7 weiteren Autor:innen. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: STATE GRID QINGHAI ELECTRIC POWER COMPANY.
Abstract (Originalsprache)
SSH honeypots serve as critical infrastructure for cyber threat intelligence, but existing LLM-based systems suffer from context window limitations causing state loss and hallucination-driven inconsistencies, making them easily detectable through simple verification tests. To address these limitations, we propose LLM-SSHH, a framework combining explicit state management with LLM generation to achieve long-term interaction consistency. The system maintains a persistent state snapshot organized as a three-component tuple capturing file system state, runtime context, and system metadata. The framework serializes the current state into LLM prompts and validates generated responses against state constraints to reject hallucinations. Validated responses update the state snapshot, forming a closed loop that ensures consistent state evolution throughout extended interactions. Experimental results demonstrate that LLM-SSHH achieves a mean detection rate of 0.150, representing a 3 to 4 times improvement over existing methods, significantly extending honeypot survivability for threat intelligence collection.
Förderung
- STATE GRID QINGHAI ELECTRIC POWER COMPANY
Zitieren
APA
Li, X., Li, N., Li, Z., Yan, L., Ma, D., Cao, H., Wang, X., & Liu, Y. (2026). LLM-SSHH: An LLM-Powered SSH Honeypot Framework via State Snapshot. Applied System Innovation, 9(5), 101. https://doi.org/10.3390/asi9050101
Vancouver
Li X, Li N, Li Z, Yan L, Ma D, Cao H, et al. LLM-SSHH: An LLM-Powered SSH Honeypot Framework via State Snapshot. Applied System Innovation. 2026;9(5):101. doi:10.3390/asi9050101
BibTeX
@article{Li2026,
author = {Li, Xiang and Li, Nanfang and Li, Zongrong and Yan, Lijun and Ma, Denghui and Cao, Haishan and Wang, Xu and Liu, Yu},
title = {LLM-SSHH: An LLM-Powered SSH Honeypot Framework via State Snapshot},
journal = {Applied System Innovation},
year = {2026},
volume = {9},
number = {5},
pages = {101},
doi = {10.3390/asi9050101}
}
EUVIMED