Skip to content
InfoResearchPreprintLLM-specific

Adaptive LLM-Driven Honeypots vs. LLM-Driven Attackers: Does Narrative Coherence Improve Deception?

Published
Record updated
View JSON

Summary

Researchers propose narrative deception, a reactive honeypot strategy in which an LLM-powered defender maps each observed attacker command to a MITRE ATT&CK technique and deploys mutually referential artefacts on an emulated Ubuntu host during the intrusion. In a 1,150-session campaign, coherent scenarios raised the median session length of advanced attackers from 40 to 165 commands and cut their abandonment from 86% to 52%. Nearly all sessions ended through loss of interest rather than detection.