Malicious-Traffic Classification Using Deep Learning with Packet Bytes and Arrival Time.

摘要: Internet technology is rapidly developing through the development of computer technology. However, we haven been experiencing problems such as malware with these developments. Various methods detection have studied for years to respond malicious codes. There are three main ways classify traffic. They port-based, payload-based and a machine learning method. We attempt traffic using CNN which one deep algorithms. The features use packet’s size its arrival time. time information extracted then converted into an image file. used what type attack is. accuracy proposed technique was 95%, showed very high performance, proving that classification possible.