TY - GEN
T1 - Towards Stable Backdoor Purification through Feature Shift Tuning
AU - Min, Rui
AU - Qin, Zeyu
AU - Shen, Li
AU - Cheng, Minhao
N1 - Publisher Copyright:
© 2023 Neural information processing systems foundation. All rights reserved.
PY - 2023
Y1 - 2023
N2 - It has been widely observed that deep neural networks (DNN) are vulnerable to backdoor attacks where attackers could manipulate the model behavior maliciously by tampering with a small set of training samples. Although a line of defense methods is proposed to mitigate this threat, they either require complicated modifications to the training process or heavily rely on the specific model architecture, which makes them hard to deploy into real-world applications. Therefore, in this paper, we instead start with fine-tuning, one of the most common and easy-to-deploy backdoor defenses, through comprehensive evaluations against diverse attack scenarios. Observations made through initial experiments show that in contrast to the promising defensive results on high poisoning rates, vanilla tuning methods completely fail at low poisoning rate scenarios. Our analysis shows that with the low poisoning rate, the entanglement between backdoor and clean features undermines the effect of tuning-based defenses. Therefore, it is necessary to disentangle the backdoor and clean features in order to improve backdoor purification. To address this, we introduce Feature Shift Tuning (FST), a method for tuning-based backdoor purification. Specifically, FST encourages feature shifts by actively deviating the classifier weights from the originally compromised weights. Extensive experiments demonstrate that our FST provides consistently stable performance under different attack settings. Without complex parameter adjustments, FST also achieves much lower tuning costs, only 10 epochs. Our codes are available at https://github.com/AISafety-HKUST/stable_backdoor_purification.
AB - It has been widely observed that deep neural networks (DNN) are vulnerable to backdoor attacks where attackers could manipulate the model behavior maliciously by tampering with a small set of training samples. Although a line of defense methods is proposed to mitigate this threat, they either require complicated modifications to the training process or heavily rely on the specific model architecture, which makes them hard to deploy into real-world applications. Therefore, in this paper, we instead start with fine-tuning, one of the most common and easy-to-deploy backdoor defenses, through comprehensive evaluations against diverse attack scenarios. Observations made through initial experiments show that in contrast to the promising defensive results on high poisoning rates, vanilla tuning methods completely fail at low poisoning rate scenarios. Our analysis shows that with the low poisoning rate, the entanglement between backdoor and clean features undermines the effect of tuning-based defenses. Therefore, it is necessary to disentangle the backdoor and clean features in order to improve backdoor purification. To address this, we introduce Feature Shift Tuning (FST), a method for tuning-based backdoor purification. Specifically, FST encourages feature shifts by actively deviating the classifier weights from the originally compromised weights. Extensive experiments demonstrate that our FST provides consistently stable performance under different attack settings. Without complex parameter adjustments, FST also achieves much lower tuning costs, only 10 epochs. Our codes are available at https://github.com/AISafety-HKUST/stable_backdoor_purification.
UR - http://www.scopus.com/inward/record.url?scp=85180339345&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85180339345&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85180339345
T3 - Advances in Neural Information Processing Systems
BT - Advances in Neural Information Processing Systems 36 - 37th Conference on Neural Information Processing Systems, NeurIPS 2023
A2 - Oh, A.
A2 - Neumann, T.
A2 - Globerson, A.
A2 - Saenko, K.
A2 - Hardt, M.
A2 - Levine, S.
PB - Neural information processing systems foundation
T2 - 37th Conference on Neural Information Processing Systems, NeurIPS 2023
Y2 - 10 December 2023 through 16 December 2023
ER -