IoT device fingerprinting for relieving pressure in the access control

Abstract

As mass devices access to network in the era of the Internet of Things (IoT), the network access control becomes more important. Traditional authentication mechanisms are no longer suitable for IoT devices with limited physical and computational resources because of their complexity. This problem can be solved by the device fingerprinting, which can identify devices only by their traffic characteristics. However, existing device fingerprinting technologies cannot accurately identify devices' type from the same manufacturer which equips these devices with similar hardwares and softwares. Therefore, we proposed the TSMC-SVM algorithm which introduced the cosine similarity into the SVM for improving the identification accuracy of these similar devices described above. Experiments illustrate that the average identification accuracy of the TSMC-SVM reaches 93.2%.