Unsupervised detection of malware in persistent web traffic

摘要: Persistent network communication can be found in many instances of malware. In this paper, we analyse the possibility leveraging low variability persistent malware for its detection. We propose a new method capturing statistical fingerprints connections and employ outlier detection to identify malicious ones. Emphasis is put on using minimal information possible make our very lightweight easy deploy. Anomaly commonly used security, yet best knowledge, there are not works focusing itself, without making further assumptions about purpose.