In a controlled LLM multi-agent simulation, adaptive insiders exhibit statistically lower peer suspicion in-degree than random innocents, inverting the expected detection signal while UEBA ranks remain unaffected.
Insider threat test dataset (r4.2)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
dataset 1
citation-polarity summary
fields
cs.CR 1years
2026 1verdicts
CONDITIONAL 1roles
dataset 1polarities
background 1representative citing papers
citing papers explorer
-
HBEE: Human Behavioral Entropy Engine -- Pre-Registered Multi-Agent LLM Simulation of Peer-Suspicion-Based Detection Inversion
In a controlled LLM multi-agent simulation, adaptive insiders exhibit statistically lower peer suspicion in-degree than random innocents, inverting the expected detection signal while UEBA ranks remain unaffected.