Journal
IEEE TRANSACTIONS ON RELIABILITY
Volume 72, Issue 2, Pages 431-444Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TR.2022.3179491
Keywords
Sensors; Eigenvalues and eigenfunctions; Matrix decomposition; Frequency modulation; Neural networks; Correlation; Training data; Adversarial attack; data poisoning; internet-of-things (IoTs); spectrum sensing; waveform design
Ask authors/readers for more resources
This article investigates the unique advantages and security risks of deep learning in spectrum sensing in cognitive radio-based Internet of Things networks. By combining traditional interference methods with data poisoning attacks, a new adversarial attack method is proposed to reduce sensing accuracy, while introducing a novel design of jamming waveform to enhance interference capability.
Cognitive radio-based Internet of Things (CR-IoT) network provides a solution for IoT devices to efficiently utilize spectrum resources. Spectrum sensing is a critical problem in CR-IoT network, which has been investigated extensively based on deep learning (DL). Despite the unique advantages of DL in spectrum sensing, the black-box and unexplained properties of deep neural networks may lead to many security risks. This article considers the fusion of traditional interference methods and data poisoning which is an attack method on the training data of a machine learning tool. We propose a new adversarial attack for reducing the sensing accuracy in DL-based spectrum sensing systems. We introduce a novel design of jamming waveform whose interference capability is reinforced by data poisoning. Simulation results show that significant performance enhancement and higher mobility can be achieved compared with traditional white-box attack methods.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available