Today's wireless technologies are largely based on inflexible designs, which make them inefficient and prone to a variety of wireless attacks. To address this key issue, wireless receivers will need to (i) infer on-the-fly the physical layer parameters currently used by transmitters; and if needed, (ii) change their hardware and software structures to demodulate the incoming waveform. In this paper, we introduce PolymoRF, a deep learning-based polymorphic receiver able to reconfigure itself in real time based on the inferred waveform parameters. Our key technical innovations are (i) a novel embedded deep learning architecture, called RFNet, which enables the solution of key waveform inference problems, and (ii) a generalized hardware/software architecture that integrates RFNet with radio components and signal processing. We prototype PolymoRF on a custom software-defined radio platform and show through extensive over-the-air experiments that PolymoRF achieves throughput within 87% of a perfect-knowledge Oracle system, thus demonstrating for the first time that polymorphic receivers are feasible.
It has been forecast that over 50 billion mobile devices will be soon connected to the Internet, creating the biggest network the world has ever seen.3 However, only very recently has the community started to acknowledge that squeezing billions of devices into tiny spectrum portions will inevitably create disruptive levels of interference. Although Mitola and Maguire first envisioned the concept of "cognitive radios" 20 years ago,8 today's commercial wireless devices still use inflexible wireless standards such as Wi-Fi and Bluetooth—and thus, are still very far from being truly real-time reconfigurable. Just to give an example of the seriousness of the spectrum inflexibility issue, DARPA has recently invested to launch the spectrum collaboration challenge (SC2), where the target is to design spectrum access schemes that "[…] best share spectrum with any network(s), in any environment, without prior knowledge, leveraging on machine-learning techniques."25
No entries found