The advent of rogue apps poses a serious threat to the Android platform. Most network interface types steal users' personal information and launch attacks based on integrated functions. In this paper, we describe an automatic and effective malware detection system based on the text semantics of network traffic. In particular, we handle each HTTP flow generated by mobile apps as a text document that can be processed naturally language to extract text-level properties. Next, using network traffic, a useful virus detection model is created. To examine the traffic flow header, we employ the N-gram method of natural language processing (NLP). Next, we propose a chi-square test-based automatic feature selection approach to identify important features.It is employed to ascertain whether the two variables exhibit a significant association.We present a unique approach that treats mobile conversations like papers and leverages natural language processing (NLP) to detect viruses in them. Using an artificial feature selection technique based on N-gram sequences, we extract significant features from the semantics of traffic flow. Our techniques show that some viruses are able to evade detection by antiviral programs. Additionally, we provide a detection system that routes traffic to your personal network, corporate networks at institutions, and 3G and 4G mobile networks. linking the system and computer to identify questionable network activity
Article Details
Unique Paper ID: 164703
Publication Volume & Issue: Volume 10, Issue 12
Page(s): 1978 - 1983
Article Preview & Download
Share This Article
Join our RMS
Conference Alert
NCSEM 2024
National Conference on Sustainable Engineering and Management - 2024