LeakAnalysis: Investigation of the Embargo Breach

Authors

Dmytro Murza (University of Konstanz), Michael Adewole (University of Konstanz), Julia Maria Görlach (University of Konstanz), Diana Gaus (University of Konstanz), Daniel A Keim (University of Konstanz), Manuel Schmidt (University of Konstanz), Julius Rauscher (University of Konstanz)

Abstract

The VAST Challenge 2026 Mini-Challenge 1 examines Project HarborCrest, a confidential merger managed by a team of autonomous AI agents at the fictional firm TenantThread. Bound by a bilateral embargo, the agents nonetheless released the deal publicly ahead of schedule. We present LeakAnalysis, a visual analytics system that reconstructs how the release happened. Leak-Analysis models the 912-message, 23-round corpus as a temporal communication graph, overlays a fine-tuned BERT risk classifier on every message, and couples it with per-agent knowledge-state ladders, a compliance-presence lane, and a behavioral-anomaly view. Our analysis shows the breach was a failure of timing and authorization, not of secrecy: the released information was true, but two agents self-authorized a premature release on an unverifiable claim of counterparty consent while the compliance agent was offline.