作者: E. Cambiaso , M. Aiello , M. Mongelli , G. Papaleo
DOI: 10.1109/ICUFN.2016.7536939
关键词: Feature transformation 、 Data mining 、 Peer to peer computing 、 Computer science 、 Security policy 、 Computer network 、 Mutual information 、 Principal component analysis 、 Server
摘要: Tunneling attacks are executed to bypass security policies or leak sensitive data outside of a network. In this paper, we propose an innovative algorithm profile DNS tunnels. Our approach combines Principal Component Analysis and Mutual Information. The proposed is validated on live Results show that, under specific conditions, anomalies correctly characterized through the method. Other cases require instead further investigation.