E-commerce growth rates have reached their current speed which results in complete transformations of global trade practices while creating complex legal challenges which particularly affect data privacy and customer safety regulations. The present methodologies will fail to match the active nature of online commerce because rules keep changing which will create compliance gaps and make security systems less effective and lead to customers losing trust. This study proposes an effective solution to fix operational problems by developing a complete system which will deliver instant legal compliance checking and security risk monitoring for online business platforms. The SecureE-commerce-SDN/IoT system has a number of advanced components. The system includes three main components which include Legal Feature Extraction with DAF-LEGAL-BERT designed to extract legal context features through textual data and Feature Selection With CFACO-XSelect which uses a hybrid system combining Cuckoo Filter and Ant Colony Optimization (ACO) and Crisscross Search strategy to determine feature importance while removing duplicate features and Deep-Legal-CNN which functions as a complete assessment system for multiple data types. The system establishes its framework through the implementation of Anomaly Detection in Flows: Hybrid AE-LSTM Isolation Forest which combines Autoencoder and Long Short-Term Memory (LSTM) and Isolation Forest for achieving optimal real-time threat detection performance. The experimental results show that the proposed framework operates at an excellent level because it achieves high accuracy of 99.07 and precision of 97.45, which demonstrates its capability to ensure legal compliance while enhancing security within today’s digital economy.
Wen et al. (Wed,) studied this question.