@inproceedings{3ff2467a08084efbae72d57805ce1232,
title = "An Improved Method for Making CNN Immune to Backdoor Attack by Activating Clustering",
abstract = "When a neural network is trained with a data set from an untrusted source, an attacker can insert poisoned data with a backdoor trigger into the data set to make the neural network make wrong decisions. By using Activation Clustering over convolutional neural networks, we propose an improved method for defensing backdoor attacks in the process of data collection and preparation. Experimental results show that this method can reliably protect neural networks from the interference of malicious data during training. The essence of this method is making a neural network to learn the feature of the trigger and classify the toxic data into a separate class. The structure of the existing model is also optimized to make the size of the model lightweight.",
keywords = "Activation Clustering, Backdoor Attack, Machine learning, Neural Network, Poison data",
author = "Yuang Zhou and Yichen Lei and Limin Yu and Xianyao Li and Dingding Chen and Tongpo Zhang",
note = "Funding Information: ACKNOWLEDGMENT This research was supported by the Enhancement Fund of XJTLU (REF-19-01-04). Publisher Copyright: {\textcopyright} 2022 IEEE.; 6th International Symposium on Computer Science and Intelligent Control, ISCSIC 2022 ; Conference date: 11-11-2022 Through 13-11-2022",
year = "2022",
month = nov,
day = "11",
doi = "10.1109/ISCSIC57216.2022.00012",
language = "English",
series = "Proceedings - 2022 6th International Symposium on Computer Science and Intelligent Control, ISCSIC 2022",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1--6",
booktitle = "Proceedings - 2022 6th International Symposium on Computer Science and Intelligent Control, ISCSIC 2022",
}