Sep 2026· Arab Journal of Forensic Sciences & Forensic Medicine· 0 citations· 12 references
TL;DR
The proposed model reformulates WannaCry recognition as a binary classification task and delivers better results than the classical algorithms including Random Forest, SVM, and XGBoost among other deep learning baselines.
Abstract
Ransomware is a significant cybersecurity risk that keeps increasing and threats like the WannaCry keep showing the need to be more intelligent and adaptive in detection methods. This paper presents DeepRansom, a powerful deep learning model that has been designed to detect WannaCry ransomware in complex malware environments with high precision and in a transparent manner. The architecture combines the feature selection of TabNet and the learning context of the FT-Transformer to create a dual-model architecture that can provide performance and interpretability. DeepRansom was trained and tested on a broad dataset of 21,752 samples of 26 malware families with 11 key ransomware variants. The proposed model reformulates WannaCry recognition as a binary classification task and delivers better results than the classical algorithms including Random Forest, SVM, and XGBoost among other deep learning baselines. The experiments have proven accuracy of 99.82%, precision of 97.89%, recall of 93.94% and AUC of 0.99% with strong generalization and low false positives. In addition, the SHAP-based analysis of interpretability shows that the predictions obtained by DeepRansom are based on the appropriate behavioral and structural predictors, which supports the idea of its implementation in the practice of network forensics and threat intelligence missions.
The study involves a thorough comparison of such ML classifiers as Support Vector Machines, Random Forest, and boosted algorithms on their performance, efficiency, and versatility, and demonstrates the potential offered by machine learning powered static analysis for the development of efficient future ransomware prote...
Suvarna Bhatsangave, Rajkumar Jain· International Conference on...· 0 citations
The findings show that ensemble learning techniques, especially XGBoost, are very successful in classifying multi-class malware and can be used in practical cybersecurity systems.
Juveriya Rasheed, Umar Farooq· International Journal of Eng...· 0 citations
The experimental results show that the Support Vector Machine (SVM) model shows better results than other classifiers for ransomware detection, and has the lowest logarithmic loss, demonstrating superior effectiveness.
Kabita Dhital· National College of Computer...· 0 citations
—The growing difficulty of ransomware attacks highlights the urgent need for intelligent, real-time detection strategies that can mitigate threats before data encryption occurs. Traditional single-source detection methods often fail to identify rapidly evolving ransomware variants during their early encryption stages....
S. A. Wadho, Aun Yichiet, A. Mohammed et al.· Journal of Advances in Infor...· 0 citations
This survey describes and combines results from the following research approaches: dynamic API Modelling, CTI-enhanced analysis, early detection strategies, and MITRE ATT&CK-based behavioural modelling, to present a full picture of intelligent, explainable, and response-aware ransomware defence systems and highlight is...
Mohammed Abd Alkareem Abd, Wasan Saad Ahmed· Bilad Alrafidain Journal for...· 0 citations
An advanced framework based on the sliding window technique to collect ten consecutive records, enabling deep learning models to extract hidden time patterns between attacks is proposed, suggesting that using sliding window technology with cached deep learning models enhances their ability to detect time-period pattern...