Modulation Classification (MC) refers to the problem of classifying the modulation class of a wireless signal. In the wireless communications pipeline, MC is the first operation performed on the received signal and is critical for reliable decoding. This paper considers the problem of secure modulation classification, where a transmitter (Alice) wants to maximize MC accuracy at a legitimate receiver (Bob) while minimizing MC accuracy at an eavesdropper (Eve). The contribution of this work is to design novel adversarial learning techniques for secure MC. In particular, we present adversarial filtering based algorithms for secure MC, in which Alice uses a carefully designed adversarial filter to mask the transmitted signal, that can maximize MC accuracy at Bob while minimizing MC accuracy at Eve. We present two filtering based algorithms, namely gradient ascent filter (GAF), and a fast gradient filter method (FGFM), with varying levels of complexity. Our proposed adversarial filtering based approaches significantly outperform additive adversarial perturbations (used in the traditional ML community and other prior works on secure MC) and also have several other desirable properties. In particular, GAF and FGFM algorithms are a) computational efficient (allow fast decoding at Bob), b) power-efficient (do not require excessive transmit power at Alice); and c) SNR efficient (i.e., perform well even at low SNR values at Bob).
Ionospheric conditions are variable in nature and can cause destructive interference to transmissions made in the High Frequency (HF) band, which ranges from 3-30 MHz. This poses a problem as the HF band is a critical frequency range for various applications (i.e. emergency, military). To manage these dynamic conditions, intelligent techniques should be implemented at the transmitter and receiver to properly maintain reliable communications. In this paper, we present work deriving components of a cognitive HF transceiver with agents called cognitive engines (CEs) operating at the transmitter and receiver. At the transmitter, cognition is employed to determine the combination of modulation and coding techniques that maximize throughput. At the receiver, cognition is implemented to derive the best parameters for equalization (i.e. tap length, step size, filter type, etc.) Results are presented showing that the individual components are able to satisfy their objectives. A discussion is also provided surveying recent research efforts pertaining to the development of cognitive methods for the Automatic Link Establishment (ALE) protocol, a common networking methodology for HF stations.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.