Abstract
In recent years, malware detection has become necessary to improve system performance and prevent programs from infecting your computer. Signature-based malware failed to detect most new organisms. This article presents the hybrid technique to automatically generate and classify malicious signatures. The hybrid method is called the ANFIS-SSA approach. The hybrid system includes the Adaptive Neuro Fuzzy Interference System (ANFIS) and the Salp Swarm Optimization (SSA). Based on this observation, we propose a hybrid approach to detect malware using malware terminology and its API calls to each other. We create the master signature for the entire malware category, not the malicious template. This signature can also identify unknown extended variants of this class. We show our approach in some common malware classes, which show that each extended version of the malware class is recognized by its original signature. The proposed method is integrated into the Matlab/Simulink operating system and is comparable to existing secure methods. SAFE creates an abstract model for the malicious code and converts it to an internal representation.
Highlights
Information of the Automatic Signature Generation e word malware is a mixture of “malicious programming” and refers to programming intended to penetrate or damage a PC framework without the consent of the owner
Support Vector Machine (SVM) for matched records and ANNs for Manifest.xml documents have proven to be the smartest choices for reliably distinguishing malware on Android gadgets. e proposed structure is tested on benchmark datasets, and the results show a more remarkable precision in the detection of malware
The trademark-based procedure will be implemented as the first protection against malicious software attacks that will contaminate the functioning of the computer. is method was chosen based on the fact that this type of strategy was powerful in recognizing notable malware
Summary
Analysts have developed a wide range of strategies to detect malware and create signature. E results obtained show that the Deep Belief Networks method can achieve an accuracy of 99.1%, with the information index introduced. Specialists assemble the single model for deep learning using the entire information index. Rehman et al [12] introduced an efficient mixed framework to detect malware in Android applications. We deciphered Android apps to extract and view duplicate documents and used cutting-edge artificial intelligence calculations to effectively detect malware. To this end, a comprehensive set of investigations is performed using various classifiers such as Support Vector Machine (SVM), Decision Tree, W-J48, and K-Neighbor (KNN). E proposed structure is tested on benchmark datasets, and the results show a more remarkable precision in the detection of malware. Model was run to assess suitability, productivity, and overhead. e exploratory results indicate that the Root Agency was generally viable and that the effort required made sense
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call