SECURITY AND INTELLIGENCE MEASURE IN ONLINE MACHINE LEARNING-BASED DYNAMIC SPECTRUM SHARING NETWORKS
Date
2019
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Cognitive radio (CR) is considered as a key enabling technology for dynamic spectrum access to improve spectrum eciency. This dissertation studies the two aspects of spectrum sharing networks: Security and intelligence capabilities. In the rst part, we consider a a primary user emulation (PUE) attacker that can send falsied primary user signals and prevent the secondary user from utilizing the available channel. The best attacking strategies that an attacker can apply have not been well studied. In this thesis, for the rst time, we study optimal