Abstract
User authentication is the critical first step of network security to detect identity-based attacks and prevent subsequent malicious attacks. However, the increasingly dynamic mobile environments make it harder to always apply the cryptographic-based methods for user authentication due to their infrastructural and key management overhead. Exploiting non-cryptographic-based techniques grounded on physical layer properties to perform user authentication appears promising. To ensure the security of mobile devices in dynamic networks, we explore to use fine-grained channel state information (CSI), which is available from off-the-shelf WiFi devices, to perform proactive user authentication. We propose a user-authentication framework that has the capability to proactively request CSI and build the user profile resilient to the presence of the spoofer. Our machine learning based user-authentication techniques can distinguish two users even when they possess similar signal fingerprints and detect the existence of the spoofer in dynamic network environments. Extensive experiments in both office and apartment environments show that our framework can remove the effect of signal outliers and achieve higher authentication accuracy compared to existing approaches that use received signal strength (RSS).