Cognitive Cyber Crimes in the Era of Artificial Intelligence

25Cognitive Cybersecurity for Protecting Rural Artisan E-Commerce Platforms

Devbrath*, Kriti Bhaswar Singh, Neha Aggarwal and Kuntal Dutta

Department of Commerce and Financial Studies, Central University of Jharkhand, Ranchi, Jharkhand, India

Abstract

Rural artisan e-commerce platforms have emerged as critical enablers of cultural preservation and economic empowerment; however, their increasing digital presence exposes them to evolving cyber threats such as phishing, data manipulation, and fraudulent transactions. This study proposes a Cognitive Cybersecurity Framework (CCF) that integrates federated deep neural networks (FDNNs) with context-aware cognitive reasoning to secure rural digital marketplaces against adversarial activities. The framework was evaluated using the UNSW-NB15 dataset, which provides a comprehensive collection of normal and malicious network traffic instances (2.5 million records across nine attack categories), enabling realistic testing of cyber threat detection in e-commerce environments. The proposed FDNN-CCF model incorporates attention-based cognitive embedding, behavioral profiling of artisan transaction flows, and adaptive anomaly scoring, which collectively enhance detection precision while minimizing false positives. Experimental results show that the system achieves an overall accuracy of 98.62%, F1 score of 98.48%, precision of 98.71%, and recall of 98.25%, outperforming traditional machine learning baselines such as gradient boosting (95.3%) ...