Signature identification and user activity analysis on WhatsApp Web through network data

WhatsApp messenger is a popular instant messaging application that employs end-to-end encryption for communication. Web the browser-based implementation of messenger. Users communicate securely using SSL protocol. Encryption and use common port communication by multiple applications poses challenge in traffic classification identification. It highly needed to analyze network purpose QoS, Intrusion Detection specific classification. In this paper, we have done analysis on packets captured through data transfer whatsApp web. result, explored user activities such as message texting, contact sharing, voice message, location media status viewing. Packet level reveal patterns encrypted This pattern identified across packet lengths Other important features ability view being sent. We read unread these exposing signatures layer. These are with help TLS header information traces. Various other presented our study relevant version v0.3.2386. Also work machine learning based classifier trained classify malicious, normal traffic. From results it clear SVM gives highest accuracy 0.9666.