RF Domain Backdoor Attack on Signal Classification via Stealthy Trigger
- 22 May 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 23 (12) , 11765-11780
Abstract
Deep learning (DL) has recently become a key technology supporting radio frequency (RF) signal classification applications. Given the heavy DL training requirement, adopting outsourced training is a practical option for RF application developers. However, the outsourcing process exposes a security vulnerability that enables a backdoor attack. While backdoor attacks have been explored in the vision domain, it is rarely explored in the RF domain. In this work, we present a stealthy backdoor attack that targets DL-based RF signal classification. To realize such an attack, we extensively explore the characteristics of the RF data in different applications, which include RF modulation classification and RF fingerprint-based device identification. Then, we design a training-based backdoor trigger generation approach with different optimization procedures for two backdoor attack scenarios (i.e., poison-label and clean-label). Extensive experiments on two RF signal classification datasets show that the attack success rate is over 99.2%, while its classification accuracy for the clean data remains high (i.e., less than a 0.6% drop compared to the clean model). The low NMSE (less than 0.091) indicates the stealthiness of the attack. Additionally, we demonstrate that our attack can bypass existing defense strategies, such as Neural Cleanse and STRIP.Keywords
Funding Information
- National Science Foundation (CNS2114220, CCF1909963, CNS1801630, CNS2120276, CCF2000480, CNS2145389)
This publication has 29 references indexed in Scilit:
- Not All Samples Are Born Equal: Towards Effective Clean-Label Backdoor AttacksPattern Recognition, 2023
- RIBAC: Towards Robust and Imperceptible Backdoor Attack against Compact DNN2022
- Anomaly Detection with Autoencoders for Spectrum Sharing and Monitoring2022
- Fooling a Face Recognition System with a Marker-Free Label-Consistent Backdoor Attack2022
- Privacy-Preserving Deep Learning on Machine Learning as a Service—a Comprehensive SurveyIEEE Access, 2020
- Clean-Label Backdoor Attacks on Video Recognition Models2020
- Trojan Attacks on Wireless Signal Classification with Adversarial Machine Learning2019
- BadNets: Evaluating Backdooring Attacks on Deep Neural NetworksIEEE Access, 2019
- Convolutional Radio Modulation Recognition Networks2016
- On the use of the normalized mean square error in evaluating dispersion model performanceAtmospheric Environment. Part A. General Topics, 1993