@inproceedings{87d674c60b7844b8ad5846ea85749fd3,
title = "BadRes: Reveal the Backdoors Through Residual Connection",
abstract = "Generally, residual connections are indispensable network components in building Convolutional Neural Networks(CNNs) and Transformers for various downstream tasks in Computer Vision(CV), which encourages skip/short cuts between network blocks. However, the layer-by-layer loopback residual connections may also hurt the model's robustness by allowing unsuspecting input. In this paper, we proposed a simple yet strong backdoor attack method called BadRes, where the residual connections play as a turnstile to be deterministic on clean inputs while unpredictable on poisoned ones. We have performed empirical evaluations on four datasets with ViT and BEiT models, and the BadRes achieves 97\% attack success rate without any performance degradation on clean data. Moreover, we analyze BadRes with state-of-the-art defense methods and reveal the fundamental weakness lying in residual connections.",
keywords = "Backdoor attack, neural networks, residual connection",
author = "Mingrui He and Tianyu Chen and Haoyi Zhou and Shanghang Zhang and Jianxin Li",
note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023 ; Conference date: 04-06-2023 Through 10-06-2023",
year = "2023",
doi = "10.1109/ICASSP49357.2023.10094691",
language = "英语",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings",
address = "美国",
}