关键词：通信；计算机网络安全；指纹；设备识别；特征抽取
摘 要：This research was performed to expand AFIT's Radio Frequency 'Distinct Native Attribute' (RF-DNA) fingerprinting process to support IEEE 802.15.4 ZigBee communication network applications. The fingerprints were constructed using a 'hybrid' pool of emissions collected under a range of conditions, including anechoic chamber and an indoor office environment where dynamic multi-path and signal degradation factors were present. The RF-DNA fingerprints were input to a Multiple Discriminant Analysis, Maximum Likelihood (MDA/ML) discrimination process and a 1 vs. many 'Looks most like' classification assessment made. The hybrid MDA model was also used for 1 vs. 1 'Looks how much like' verification assessment. ZigBee Device Classification performance was assessed using both full and reduced dimensional fingerprint sets. Reduced dimensional subsets were selected using Dimensional Reduction Analysis (DRA) by rank ordering (1) pre-classification KS-Test p-values and (2) post-classification GRLVQI feature relevance values. Assessment of Zigbee device ID verification capability.