SmsNet: A New Deep Convolutional Neural Network Model for Adversarial Example Detection
Document Type
Article
Publication Date
1-1-2022
Abstract
The emergence of adversarial examples has had a significant impact on the development and application of deep learning. In this paper, a novel convolutional neural network model, the stochastic multifilter statistical network (SmsNet), is proposed for the detection of adversarial examples. A feature statistical layer is constructed to collect statistical data of feature map output from each convolutional layer in SmsNet by combining manual features with a neural network. The entire model is an end-to-end detection model, so the feature statistical layer is not independent of the network, and its output is directly transmitted to the fully connected layer by a short-cut connection called the SmsConnection. Additionally, a dynamic pruning strategy is introduced to simplify the model structure for better performance. The experiments demonstrate the effectiveness of the network structure and pruning strategy, and the proposed model achieves high detection rates against state-of-the-art adversarial attacks.
Identifier
85099598500 (Scopus)
Publication Title
IEEE Transactions on Multimedia
External Full Text Location
https://doi.org/10.1109/TMM.2021.3050057
e-ISSN
19410077
ISSN
15209210
First Page
230
Last Page
244
Volume
24
Recommended Citation
Wang, Jinwei; Zhao, Junjie; Yin, Qilin; Luo, Xiangyang; Zheng, Yuhui; Shi, Yun Qing; and Jha, Sunil Kr, "SmsNet: A New Deep Convolutional Neural Network Model for Adversarial Example Detection" (2022). Faculty Publications. 3503.
https://digitalcommons.njit.edu/fac_pubs/3503