Recognition of Abnormal Proxy Voice Traffic in 5G Environment Based on Deep Learning^*

With the commercial use of the fifth generation (5G), the rapid popularization of mobile Over- The- Top (OTT) voice applications has brought high-quality voice communication methods to users. The intelligent Internet in the 5G era makes communication terminals not limited to mobile phones. The complex communication environment has higher requirements for the security of data transmission between various terminals to prevent the system from being monitored or breached. At present, many OTT users use encrypted proxy technology to get rid of certain restrictions of network operators, prevent their private information from leaking, and ensure communication security. However, in some cases the encryption proxy may be subject to configuration error or maliciously attacked makes the encryption ineffective. The resulting abnormal proxy traffic may cause privacy leakage when users use voice services. However, little effort has been put on fingerprint the effectiveness of encryption for proxy voice traffic in a 5G environment. To this end, we adopt the VGG deep learning method to identify agent speech traffic, compare it with common deep learning methods, and study the impact on model performance with less abnormal traffic. Extensive experimental results show that the deep learning method we use can identify abnormal encrypted proxy voice traffic with the accuracy up to 99.77%. Moreover, VGG outperform other DL methods on indentifying the encryption algorithms of normal encrypted proxy traffic.