Decision trees to detect malware in cloud computing environment
Poovidha Ayyappa, Govindu Kiran Kumar Reddy, Katamreddy Siva Satish, Prakash Rachakonda, Pujari Manjunatha · 2023
The internet has become a source of many security threats with the development of wireless communication. Malware detection system (MDS) finds attacks on a system and is able to detect intruders. The MDS was previously applied with various machine learning (ML) techniques to improve its ability to detect intruders and increase its accuracy with the detection of intruders. This paper&s;s goal is to suggest a methodology for creating effective MDS utilizing principal component analysis (DECISION TREE ANALYSIS) and random forest classification. The dataset&s;s dimensions will be lowered, and categorizing the data will aided by random forest. According to the results obtained, the accuracy of this approach is superior to SVM, Nave Bayes, and Decision Trees. This technique results in 3.24 minute performance times, a 96.78% accuracy rate, and a 0.21% error rate.