Enhancing OSN Security: Detecting Email Hijacking and DNS Spoofing Using Energy Consumption and Opcode Sequence Analysis

The rapid increase in automation within Online Social Networks (OSNs) has led to a surge in cyber threats, notably Email Hijacking and DNS (Domain Name System) Spoofing, which leverage malicious scripts to manipulate traffic, steal credentials, and evade detection. Traditional security mechanisms fail to effectively identify such automation-based attacks, necessitating an advanced detection framework. Objective & Purpose-This study introduces the Automated Social Network Attack Detection Model (ASNADM), which combines Energy Consumption Footprint (EComp-FP) Analysis and Automated Software Opcode Sequence Analysis (ASOSA-OSM- opcode sequence mining) for high-precision OSN security. EComp-FP detects deviations in power consumption linked to malicious automation tools, while ASOSA-OSM analyzes opcode sequences to differentiate between benign and attack behaviors. The Self-Adaptive Fuzzy Pattern Matching Clustering (SAFPMC) Algorithm enhances classification accuracy, reducing false alarms and improving real-time threat detection. Methodology and DatasetThe model was rigorously evaluated using the SPEMC-15K-E (Spam Email Classification dataset in English) dataset (15,000 samples: 7,500 benign, 7,500 malicious). EComp-FP achieved 99.87% accuracy with a 1.4W power deviation, while ASOSA-OSM attained 99.81% accuracy, detecting automation tools with an Opcode Frequency Variance (OFV) of 8.7 in malicious samples versus 3.5 in benign ones. The hybrid EComp (Energy Consumption) + OSA (Opcode Sequence Analysis) model outperformed both standalone methods, achieving 99.93% accuracy, 99.91% F1-score, a false positive rate of just 0.07%, and a false negative rate of 0.05%. Among classifiers, the SelfAdaptive Soft Fuzzy C-Means (SSFCM) Hybrid model achieved the highest performance, with 99.93% accuracy, 99.85% precision, 99.9% recall, and the lowest misclassification rate of 0.05%, surpassing Decision Tree (DT), KNearest Neighbors (KNN), Random Forest (RF), and Support Vector Machine (SVM). Result - Optimization techniques significantly improved real-time detection efficiency. The SAFPMC algorithm reduced detection latency by 35%, while parallel processing lowered computational overhead by 31%. Feature selection improved classification speed by 27%, and federated learning reduced processing load by 25%, enabling scalable, real-time OSN threat monitoring. This study presents an advanced hybrid detection framework for OSN security, combining energy consumption profiling and opcode sequence analysis to detect email hijacking and DNS spoofing attacks. The model achieves a 99.92% detection precision, a 99.89% real-time accuracy, and reduces computational overhead by 31%, making it a robust and efficient solution for securing online social networks. These findings confirm that combining energy profiling and opcode sequence analysis is highly effective in detecting automation-based OSN threats. Future work will focus on integrating deep learning (DL) for anomaly detection, AI (artificial intelligence)- driven botnet defense, and enhancing large-scale OSN threat mitigation strategies.