Defeating Super-Reactive Jammers With Deception Strategy: Modeling, Signal Detection, and Performance Analysis

This paper develops a novel framework to defeat super-reactive jammer, one of the most difficult jamming attacks deal with in practice. Specifically, jammer has an unlimited power budget and is equipped self-interference suppression capability simultaneously attack listen transmitter’s activities. Consequently, dealing jammers very challenging. Thus, we introduce smart deception mechanism attract continuously channel then leverage signals transmit data based on ambient backscatter communication technology. To detect backscattered signals, maximum likelihood detector can be adopted. However, this method notorious for its high computational complexity requires model current propagation environment as well state information. Hence, propose deep learning-based that dynamically adapt any channels noise distributions. With Long Short-Term Memory network, our learn received signals’ dependencies achieve performance close optimal detector. Through simulation theoretical results, demonstrate approaches, more uses channel, better bit error rate transmitter achieve.