Semi supervised machine learning approach for DDOS detection

The appearance of malicious apps is a serious threat to the Android platform. In this paper, we propose an effective and automatic malware detection method using text semantics network traffic. particular, consider each HTTP flow generated by mobile as document, which can be processed natural language processing (NLP) extract text-level features. Later, use traffic used create useful model. We examine header N-gram from NLP. Then, feature selection algorithm based on Chi-square test identify meaningful It determine whether there significant association between two variables. novel solution perform NLP methods treating documents. apply sequence obtain features flows. Our reveal some that prevent antiviral scanners. addition, design system drive your own-institutional enterprise network, home 3G/4G network. Integrating connected computer find suspicious behaviors. Keywords: Semi supervised, machine, learning approach, detection, android