Romil Rawat

This study presents CyberSafe-EG-GWO, a hybrid framework for detecting phishing-based social engineering threats in digital communication platforms. The system integrates Entropy-Based Normalization Filtering (EBNF) to retain high-information tokens, Grey Wolf Optimization (EG-GWO) for discriminative feature selection, and SpinalNet for efficient classification. By combining statistical, contextual, and semantic embeddings, the framework achieves high accuracy while reducing feature dimensionality by 40-50%, supporting scalability for real-time deployment. Evaluations on the UCI Phishing Website and CIC-Phishing Email datasets demonstrate robust performance, with hold-out test accuracies of 95.8% and 94.3%, respectively, and average inference latency of 0.214 s per sample on GPU. Cross-validation highlights feature stability (> 85% overlap) and upper-bound accuracy of over 98%, while cross-dataset tests confirm generalization across domains. The design accommodates resource-constrained environments, with potential improvements via adaptive entropy thresholding, lightweight transformer embeddings, and interpretable decision explanations. CyberSafe-EG-GWO offers a reproducible, modular approach to real-time phishing detection, balancing precision, efficiency, and operational robustness, making it suitable for deployment in both structured and unstructured communication environments.

Background/Objectives—Traditional forensic investigations often analyze digital, physical, and criminological evidence separately, leading to fragmented timelines and reduced accuracy in reconstructing complex events. To address these gaps, this study proposes the Digital Stratigraphy Framework (DSF), inspired by archaeological stratigraphy, to integrate heterogeneous evidence into structured, temporally ordered layers. DSF aims to reduce asynchronous inconsistencies, minimize false associations, and enhance interpretability across digital, behavioral, geospatial, and excavation evidence. Methods—DSF employs Hierarchical Pattern Mining (HPM) to detect recurring behavioral patterns and Forensic Sequence Alignment (FSA) to synchronize evidence layers temporally and contextually. The framework was tested on the CSI-DS2025 dataset containing 25,000 multimodal, stratified records, including digital logs, geospatial data, criminological reports, and excavation notes. Evaluation used 10-fold cross-validation, Bayesian hyperparameter tuning, and structured train-validation-test splits. Metrics included accuracy, precision, recall, F1-score, and Stratigraphic Reconstruction Consistency (SRC), alongside ablation and runtime assessments. Results—DSF achieved 92.6% accuracy, 93.1% precision, 90.5% recall, 91.3% F1-score, and an SRC of 0.89, outperforming baseline models. False associations were reduced by 18%, confirming effective cross-layer alignment and computational efficiency. Conclusions—By applying stratigraphic principles to forensic analytics, DSF enables accurate, interpretable, and legally robust evidence reconstruction. The framework establishes a scalable foundation for real-time investigative applications and multi-modal evidence integration, offering significant improvements over traditional fragmented approaches.

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.

The proposed work objective is to adapt Online social networking (OSN) is a type of interactive computer-mediated technology that allows people to share information through virtual networks. The microblogging feature of Twitter makes cyberspace prominent (usually accessed via the dark web). The work used the datasets and considered the Scrape Twitter Data (Tweets) in Python using the SN-Scrape module and Twitter 4j API in JAVA to extract social data based on hashtags, which is used to select and access tweets for dataset design from a profile on the Twitter platform based on locations, keywords, and hashtags. The experiments contain two datasets. The first dataset has over 1700 tweets with a focus on location as a keypoint (hacking-for-fun data, cyber-violence data, and vulnerability injector data), whereas the second dataset only comprises 370 tweets with a focus on reposting of tweet status as a keypoint. The method used is focused on a new system model for analysing Twitter data and detecting terrorist attacks. The weights of susceptible keywords are found using a ternary search by the Aho-Corasick algorithm (ACA) for conducting signature and pattern matching. The result represents the ACA used to perform signature matching for assigning weights to extracted words of tweet. ML is used to evaluate Twitter data for classifying patterns and determining the behaviour to identify if a person is a terrorist. SVM (Support Vector Machine) proved to be a more accurate classifier for predicting terrorist attacks compared to other classifiers (KNN- K-Nearest Neighbour and NB-Naïve Bayes). The 1st dataset shows the KNN-Acc. -98.38% and SVM Accuracy as 98.85%, whereas the 2nd dataset shows the KNN-Acc. -91.68% and SVM Accuracy as 93.97%. The proposed work concludes that the generated weights are classified (cyber-violence, vulnerability injector, and hacking-for-fun) for further feature classification. Machine learning (ML) [KNN and SVM] is used to predict the occurrence and incident of crime. The accuracy and efficacy are evaluated using several parameters in the model.

The proposed work objective is to adopt the non-dominated sorting genetic algorithm II (NSGA-II), a type of MOEA (multi-objective evolutionary algorithms), to reduce the dimensionality and identify the most relevant features. The objectives and hypotheses tested using NSGA-II and MOEA are to develop predictive models that best fit the problem of traffic analysis, analyse the set of features associated with the dataset, and apply NSGA techniques to reduce the data dimensionality.The work used the datasets and considered the Transnational Terrorist Hostage Event (TTHE) and Counter Trafficking Data Collaborative (CTDC) datasets, which relate to global human trafficking (HTr).The method used is focused on analysing the energy consumption (Econ) with the carbon footprint (CFP) of the proposed algorithm for different values of the main parameters on different hardware platforms, where the quality of each individual is computed based on ML algorithms.The result represents the "F-measure” metric obtained from support vector machines (SVM) and the number of features in order to determine the dimensionality, the execution time, the Econ, and the CFP during the feature engineering process. To estimate performance, the parameter values are computed using SVM.The proposed work concludes that cybercrime employs and represents susceptible behaviour on the OSN Channels network. We identified the threat patterns by using NSGA-II and Econ analysis to establish connections between the variables in the dataset.