Key Words
network security, device fingerprinting, machine learning, wireless network, digital network
Knowledge
Network security, communication theory, network architecture and protocols
Introduction
Today’s data networks are becoming increasingly complex, with millions of devices ranging from small sensors, smartphones, and vehicles, to computing servers that communicate using a variety of network technologies, such as IoT, WLAN, or cellular. In addition to their heterogeneity, today’s networks are highly dynamic with nodes continuously joining and leaving the network. Moreover, today’s networks ever increasing use of wireless communications makes them quite vulnerable to security attacks, for example through device impersonation, where malicious actors capture legitimate cryptographic credentials. Not surprisingly, security attacks have increased significantly in recent years.
Device fingerprinting (DF) has emerged as a promising technique against impersonation or insider attacks in wireless networks, enabled by signal analysis. DF can considerably enhance device identification accuracy and robustness, thus significantly reducing the risk of device impersonation attacks by leveraging unique characteristics of devices at the physical and MAC layers, termed hereafter as Cross-Layer (CL)-device fingerprinting (DF). This project covers the following aspects: 1) cross-layer features extracted based on applications, such as security, management, or network performance; 2) machine learning techniques applied on the extracted features for certain applications, such as distributed learning, on-line learning, unsupervised learning; 3) security enhancements based on device fingerprinting; 4) applications scenarios, such as wifi networks, vehicular networks, etc. In the future, we are considering applying device fingerprinting techniques to digital networks applications, including distributed networks and network security schemes regeneration.
Publications
– to be updated