Lauri Loven
2 papers · Latest:
The Endogeneity of Miscalibration: Impossibility and Escape in Scored Reporting
This paper reveals an endogeneity in AI oversight: smooth scoring rules fail to elicit truthful reports from strategic agents, but sharp, step-function thresholds offer a solution.
2605.07671
Cryptography & SecurityExAI5G: A Logic-Based Explainable AI Framework for Intrusion Detection in 5G Networks
ExAI5G is an explainable AI framework for 5G intrusion detection, combining deep learning with logic-based XAI to provide high accuracy and transparent reasoning.
2604.18052
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.