Academic Journal
Enhancing Ransomware Attack Detection Using Transfer Learning and Deep Learning Ensemble Models on Cloud-Encrypted Data
| العنوان: | Enhancing Ransomware Attack Detection Using Transfer Learning and Deep Learning Ensemble Models on Cloud-Encrypted Data |
|---|---|
| المؤلفون: | Amardeep Singh, Zohaib Mushtaq, Hamad Ali Abosaq, Salim Nasar Faraj Mursal, Muhammad Irfan, Grzegorz Nowakowski |
| المصدر: | Electronics, Vol 12, Iss 3899, p 3899 (2023) |
| بيانات النشر: | MDPI AG |
| سنة النشر: | 2023 |
| المجموعة: | Directory of Open Access Journals: DOAJ Articles |
| مصطلحات موضوعية: | ransomware attack detection, transfer learning, deep learning ensemble models, cloud-encrypted data, cybersecurity, Electronics, TK7800-8360 |
| الوصف: | Ransomware attacks on cloud-encrypted data pose a significant risk to the security and privacy of cloud-based businesses and their consumers. We present RANSOMNET+, a state-of-the-art hybrid model that combines Convolutional Neural Networks (CNNs) with pre-trained transformers, to efficiently take on the challenging issue of ransomware attack classification. RANSOMNET+ excels over other models because it combines the greatest features of both architectures, allowing it to capture hierarchical features and local patterns. Our findings demonstrate the exceptional capabilities of RANSOMNET+. The model had a fantastic precision of 99.5%, recall of 98.5%, and F1 score of 97.64%, and attained a training accuracy of 99.6% and a testing accuracy of 99.1%. The loss values for RANSOMNET+ were impressively low, ranging from 0.0003 to 0.0035 throughout training and testing. We tested our model against the industry standard, ResNet 50, as well as the state-of-the-art, VGG 16. RANSOMNET+ excelled over the other two models in terms of F1 score, accuracy, precision, and recall. The algorithm’s decision-making process was also illuminated by RANSOMNET+’s interpretability analysis and graphical representations. The model’s openness and usefulness were improved by the incorporation of feature distributions, outlier detection, and feature importance analysis. Finally, RANSOMNET+ is a huge improvement in cloud safety and ransomware research. As a result of its unrivaled accuracy and resilience, it provides a formidable line of defense against ransomware attacks on cloud-encrypted data, keeping sensitive information secure and ensuring the reliability of cloud-stored data. Cybersecurity professionals and cloud service providers now have a reliable tool to combat ransomware threats thanks to this research. |
| نوع الوثيقة: | article in journal/newspaper |
| اللغة: | English |
| تدمد: | 2079-9292 |
| Relation: | https://www.mdpi.com/2079-9292/12/18/3899; https://doaj.org/toc/2079-9292; https://doaj.org/article/2b81e637de2d450c80a2017438f592b2 |
| DOI: | 10.3390/electronics12183899 |
| الاتاحة: | https://doi.org/10.3390/electronics12183899 https://doaj.org/article/2b81e637de2d450c80a2017438f592b2 |
| رقم الانضمام: | edsbas.6DFD2E2E |
| قاعدة البيانات: | BASE |
Full Text Finder | تدمد: | 20799292 |
|---|---|
| DOI: | 10.3390/electronics12183899 |