A three-component fusion architecture of LSTM, statistical, and graph modules detects fraud and AML on synthetic banking data with F1 scores of 0.787 (transactions) and 0.867 (sessions), outperforming rule-based and LSTM-only baselines.
A survey of network anomaly detection techniques,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CR 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
An AI security agent for ACMIS achieves 0.91 macro-average F1 threat detection on simulated data using anomaly detection and behavioral analytics, outperforming a 0.49 rule-based baseline with sub-300ms critical response latency.
citing papers explorer
-
An AI Security Agent for Banking: Multi-Vector Fraud and AML Detection Across Retail and Corporate Accounts
A three-component fusion architecture of LSTM, statistical, and graph modules detects fraud and AML on synthetic banking data with F1 scores of 0.787 (transactions) and 0.867 (sessions), outperforming rule-based and LSTM-only baselines.
-
An AI Security Agent for University ACMIS: Multi-Vector Threat Detection and Automated Response
An AI security agent for ACMIS achieves 0.91 macro-average F1 threat detection on simulated data using anomaly detection and behavioral analytics, outperforming a 0.49 rule-based baseline with sub-300ms critical response latency.