What type of study is this?

September 10, 2025

Comprehensive Evaluation of Machine Learning and Deep Learning Approaches for Malware Detection

Key Points

The gradient boosting model achieved the highest accuracy of 99.98% in detecting malware attacks.
Experimental results indicate machine learning models are highly effective for cybersecurity protection against malware.
This research compared several models including GRU, Random Forest, LSTM, and RNN for malware detection.
Rising malware complexity necessitates effective detection methods to mitigate cybersecurity risks.

Abstract

In an era of advancing technology, breakthrough innovations, state- of-the-art hardware development, increased computing capacity through cloud computing and supercomputers, and collaboration between research institutions and industries are the primary driv- ing forces. However, this is also accompanied by the rise in malware attacks due to increasingly complex systems and the adoption of new technologies providing vulnerabilities for attackers. High pro- cessing capabilities are exploited to develop undetectable malware, while collaboration among cybercriminals is on the rise. There- fore, effective cybersecurity protection and efforts are becoming increasingly crucial. In this study, we compared GRU, Random For- est, Gradient Boosting, LSTM, and RNN models for malware attack detection, with experimental results showing that the Gradient Boosting model achieved the highest accuracy of 99.98%.

AI에게 질문

Bookmark