No abstract

Malware is an international software disease. Research shows that the effect of malware is becoming chronic. To protect against malware detectors are fundamental to the industry. The effectiveness of such detectors depends on the technology used. Therefore, it is paramount that the advantages and disadvantages of each type of technology are scrutinized analytically. This study's aim is to scrutinize existing publications on this subject and to follow the trend that has taken place in the advancement and development with reference to the amount of information and sources of such literature. Many of the malware programs are huge and complicated and it is not easy to comprehend the details. Dissemination of malware information among users of the Internet and also training them to correctly use anti-malware products are crucial to protecting users from the malware onslaught. This paper will provide an exhaustive bibliography of methods to assist in combating malware.

ABSTRACT

No abstract

This paper aims to propose cybercrime detection and prevention model by using Support Vector Machine (SVM) andAdaBoost algorithm in order to reduce data damaging due to running of malicious codes. The performance ofthis model will be evaluated on a Facebook dataset, which includes benign executable and malicious codes. The mainobjective of this paper is to find the effectiveness of different classifiers on the Facebook dataset for crime detection.Finally, we try to compare the classifier accuracy of SVM and AdaBoost by using Weka 3.7.4 software in order to choosethe best model to classify the Facebook dataset with high accuracy.