Answers are grounded in this paper and cite their sources.
Evaluates dynamic trust in blockchain-enabled IAM systems, suggesting enhanced security and compliance.
ML-DTEM introduces a dynamic trust evaluation framework that continuously reassesses user trust throughout an active session, moving beyond traditional one-time authentication models. The framework combines XGBoost, Long Short-Term Memory (LSTM) networks, and Isolation Forest anomaly detection to compute a real-time trust score that drives adaptive access decisions (Grant, Step-Up Authentication, or Deny). To ensure transparency, compliance, and tamper-evident auditing, every access decision is recorded on a Hyperledger Fabric permissioned blockchain. The paper presents the complete system architecture, machine learning pipeline, blockchain governance layer, security analysis, and experimental evaluation using a 500,000-event enterprise IAM dataset. Experimental results achieve 97.4% classification accuracy, a 1.8% false positive rate, and sub-200 ms response latency while supporting regulatory requirements including NIST SP 800-207, GDPR, and the EU AI Act.
No takes yet. Share an insight, caveat, or question.
Sanskar Pandit (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: