A Hybrid Security Model Combining Face Spoofing Detection with Cryptocurrency Transaction Tracing for Cybercrime Investigation.

The rapid expansion of digital finance and remote identity systems has increased risks of identity spoofing and cryptocurrency fraud. Traditional security solutions treat biometric authentication and financial investigation separately, leaving exploitable gaps. This research proposes a hybrid security model integrating face spoofing detection with cryptocurrency transaction tracing. Deep learning–based facial anti-spoofing detects replay attacks, 3D mask attacks, and deepfake impersonation. Convolutional Neural Networks (CNNs) and liveness detection extract spatial–temporal features to classify real versus fake identities. Simultaneously, blockchain forensic analysis traces suspicious cryptocurrency transactions. Graph analytics, wallet clustering, and anomaly detection techniques identify illicit financial flows. The integrated framework creates a multi-layered defense for both prevention and investigation. Experimental results show higher fraud detection accuracy and reduced false acceptance rates. This approach offers a scalable cybersecurity solution for financial institutions, crypto exchanges, and law enforcement agencies.

Keywords:  Face Spoofing Detection, Facial Anti-Spoofing, Deep Learning, Convolutional Neural Networks (CNN),Liveness Detection, Blockchain Forensics, Cryptocurrency Transaction Tracing, Wallet Clustering, Anomaly Detection, Cybercrime Investigation

  Face Spoofing Detection Facial Anti-Spoofing Deep Learning Convolutional Neural Networks (CNN) Liveness Detection Blockchain Forensics Cryptocurrency Transaction Tracing Wallet Clustering Anomaly Detection Cybercrime Investigation