Paper Number

ICIS2025-1409

Paper Type

Short

Abstract

This study presents a novel approach for the proactive identification and profiling of scammers within dark web communities, using a disentangled attention-based architecture and weighted feature extraction. We enhance the detection and classification of scammer assets from obfuscated and adversarial environments by decoupling token-level features and positional contexts to improve entity boundary detection. Grounded by the instrumental genesis theory, we triangulate these assets to specific scammers in revealing key operational roles and behavioral characteristics. Furthermore, a bipartite network analysis is employed to understand the relationships between scammers and their found assets, facilitating the identification of core actors and tactical approaches. The findings contribute to both theory and practice, offering a novel, asset-centric framework for early scam detection and intervention, which will inform cybersecurity measures and enhance threat intelligence systems. The work provides a foundation for future research in real-time anomaly detection and cross-platform asset diffusion in cyber threat intelligence.

Comments

09-Cybersecurity

Share

COinS
 
Dec 14th, 12:00 AM

Cyber Threat Intelligence - Exploring Emerging Scammer Assets and Key Scammers for Proactive Information Security

This study presents a novel approach for the proactive identification and profiling of scammers within dark web communities, using a disentangled attention-based architecture and weighted feature extraction. We enhance the detection and classification of scammer assets from obfuscated and adversarial environments by decoupling token-level features and positional contexts to improve entity boundary detection. Grounded by the instrumental genesis theory, we triangulate these assets to specific scammers in revealing key operational roles and behavioral characteristics. Furthermore, a bipartite network analysis is employed to understand the relationships between scammers and their found assets, facilitating the identification of core actors and tactical approaches. The findings contribute to both theory and practice, offering a novel, asset-centric framework for early scam detection and intervention, which will inform cybersecurity measures and enhance threat intelligence systems. The work provides a foundation for future research in real-time anomaly detection and cross-platform asset diffusion in cyber threat intelligence.

When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.