TY - GEN
T1 - DETECTING BACKDOOR ATTACKS AGAINST POINT CLOUD CLASSIFIERS
AU - Xiang, Zhen
AU - Miller, David J.
AU - Chen, Siheng
AU - Li, Xi
AU - Kesidis, George
N1 - Publisher Copyright:
© 2022 IEEE
PY - 2022
Y1 - 2022
N2 - Backdoor attacks (BA) are an emerging threat to deep neural network classifiers. A classifier being attacked will predict to the attacker's target class when a test sample from a source class is embedded with the backdoor pattern (BP). Recently, the first BA against point cloud (PC) classifiers was proposed, creating new threats to many important applications including autonomous driving. Such PC BAs are not detectable by existing BA defenses due to their special BP embedding mechanism. In this paper, we propose a reverse-engineering defense that infers whether a PC classifier is backdoor attacked, without access to its training set or to any clean classifiers for reference. The effectiveness of our defense is demonstrated on the benchmark ModeNet40 dataset for PCs.
AB - Backdoor attacks (BA) are an emerging threat to deep neural network classifiers. A classifier being attacked will predict to the attacker's target class when a test sample from a source class is embedded with the backdoor pattern (BP). Recently, the first BA against point cloud (PC) classifiers was proposed, creating new threats to many important applications including autonomous driving. Such PC BAs are not detectable by existing BA defenses due to their special BP embedding mechanism. In this paper, we propose a reverse-engineering defense that infers whether a PC classifier is backdoor attacked, without access to its training set or to any clean classifiers for reference. The effectiveness of our defense is demonstrated on the benchmark ModeNet40 dataset for PCs.
UR - http://www.scopus.com/inward/record.url?scp=85130812150&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85130812150&partnerID=8YFLogxK
U2 - 10.1109/ICASSP43922.2022.9747194
DO - 10.1109/ICASSP43922.2022.9747194
M3 - Conference contribution
AN - SCOPUS:85130812150
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 3159
EP - 3163
BT - 2022 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 47th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2022
Y2 - 23 May 2022 through 27 May 2022
ER -