Locality-Sensitive IoT Network Traffic Fingerprinting for Device Identification

摘要: Engineered systems get smarter with computing capabilities, particularly through a multitude of Internet-of-Things (IoT) devices. IoT devices, however, are prone to be compromised as they often resource limited and optimized for certain task. They lack power security software hence, have become major target malicious activities. In order secure network, administrators may isolate vulnerable devices limit traffic device based on its communication needs. this article, we introduce novel approach identify an the locality-sensitive hash flow. Different from previous studies that employ machine learning, proposed does not require feature extraction data, operates in all states (e.g., setup, idle, active), retrain model when new type/version is introduced. The evaluation results different data sets show our achieves precision recall above 90% average performs equally well compared state-of-the-art learning-based methods.