TY - GEN
T1 - Stealthy Backdoor Attack on RF Signal Classification
AU - Zhao, Tianming
AU - Tang, Zijie
AU - Zhang, Tianfang
AU - Phan, Huy
AU - Wang, Yan
AU - Shi, Cong
AU - Yuan, Bo
AU - Chen, Yingying
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Recently, deep learning (DL) has become one of the key technologies 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 computer 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. Particularly, we design a training-based backdoor trigger generation approach with an optimization procedure that not only accommodates dynamic application inputs but also is stealthy to RF receivers. Extensive experiments on two RF signal classification datasets show that the average attack success rate of our backdoor attack 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). Additionally, we demonstrate that our attack can bypass existing defense strategies, such as Neural Cleanse and STRIP.
AB - Recently, deep learning (DL) has become one of the key technologies 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 computer 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. Particularly, we design a training-based backdoor trigger generation approach with an optimization procedure that not only accommodates dynamic application inputs but also is stealthy to RF receivers. Extensive experiments on two RF signal classification datasets show that the average attack success rate of our backdoor attack 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). Additionally, we demonstrate that our attack can bypass existing defense strategies, such as Neural Cleanse and STRIP.
KW - Deep Learning Security
KW - Mobile Security
KW - Radio-Frequency Backdoor Attack
KW - Wireless Communication Security
UR - http://www.scopus.com/inward/record.url?scp=85173584606&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85173584606&partnerID=8YFLogxK
U2 - 10.1109/ICCCN58024.2023.10230152
DO - 10.1109/ICCCN58024.2023.10230152
M3 - Conference contribution
AN - SCOPUS:85173584606
T3 - Proceedings - International Conference on Computer Communications and Networks, ICCCN
BT - ICCCN 2023 - 2023 32nd International Conference on Computer Communications and Networks
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 32nd International Conference on Computer Communications and Networks, ICCCN 2023
Y2 - 24 July 2023 through 27 July 2023
ER -