SINN-RD: Spline interpolation-envisioned neural network-based ransomware detection scheme. (March 2023)

• Record Type: Journal Article
• Authors: Singh, Jaskaran; Sharma, Keshav; Wazid, Mohammad; Das, Ashok Kumar
• Is Part Of: Computers & electrical engineering. Volume 106(2023)
• Publication Date: 2023-03
• Subjects: Deep learning -- Neural network -- Spline interpolation -- Ransomware -- Security -- Simulation; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2023.108601
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: Multiple kinds of ransomware are currently posing a growing threat to the Internet users. Important user data is encrypted by the trendy ransomware, and its recovery requires payment of a ransom in terms of some amount of money. The trend of crypto-currencies may be a contributing factor to the rise of ransomware attacks. From time to time, different mechanisms for detection and mitigation of ransomware attacks have been proposed. However, the performance of the ransomware detection process can be improved through the deployment of Machine Learning/Deep Learning based mechanisms. In this article, we propose a novel Spline Interpolation envisioned Neural Network based Ransomware Detection Scheme (in short, we call it as SINN-RD). Additionally, we introduce the mechanisms for normalizing the data and generating the new features from the log files. The conducted security analysis of the proposed SINN-RD proves its security against several potential attacks. The practical implementation of SINN-RD is provided to find out its impact on the essential performance parameters, like accuracy, precision, recall and F1-score. Furthermore, in the comparative study, it has been observed that the proposed SINN-RD performs better than other existing related schemes as it achieves high accuracy value of 99.83%. Graphical abstract: Highlights: A spline interpolation envisioned neural network based ransomware detection scheme (SINN-RD) is proposed. The proposed SINN-RD is proved to be secure against various possible attacks. A detailed comparative study confirms that SINN-RD achieves better accuracy than other existing schemes. The practical demonstration of SINN-RD demonstrates its impact on different performance parameters.