Journal article 220 views
Jacobian norm with Selective Input Gradient Regularization for interpretable adversarial defense
Deyin Liu 
,
Lin Yuanbo Wu,
Bo Li,
Farid Boussaid,
Mohammed Bennamoun,
Xianghua Xie ,
Chengwu Liang,
Yuanbo Wu
,
Lin Yuanbo Wu,
Bo Li,
Farid Boussaid,
Mohammed Bennamoun,
Xianghua Xie ,
Chengwu Liang,
Yuanbo Wu
Pattern Recognition, Volume: 145, Start page: 109902
Swansea University Authors:
Xianghua Xie , Yuanbo Wu
DOI (Published version): 10.1016/j.patcog.2023.109902
Abstract
Deep neural networks (DNNs) can be easily deceived by imperceptible alterations known as adversarial examples. These examples can lead to misclassification, posing a significant threat to the reliability of deep learning systems in real-world applications. Adversarial training (AT) is a popular tech...
| Published in: | Pattern Recognition |
|---|---|
| ISSN: | 0031-3203 |
| Published: |
Elsevier BV
2024
|
| Online Access: |
Check full text
|
| URI: | https://cronfa.swan.ac.uk/Record/cronfa64108 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract: |
Deep neural networks (DNNs) can be easily deceived by imperceptible alterations known as adversarial examples. These examples can lead to misclassification, posing a significant threat to the reliability of deep learning systems in real-world applications. Adversarial training (AT) is a popular technique used to enhance robustness by training models on a combination of corrupted and clean data. However, existing AT-based methods often struggle to handle transferred adversarial examples that can fool multiple defense models, thereby falling short of meeting the generalization requirements for real-world scenarios. Furthermore, AT typically fails to provide interpretable predictions, which are crucial for domain experts seeking to understand the behavior of DNNs. To overcome these challenges, we present a novel approach called Jacobian norm and Selective Input Gradient Regularization (J-SIGR). Our method leverages Jacobian normalization to improve robustness and introduces regularization of perturbation-based saliency maps, enabling interpretable predictions. By adopting J-SIGR, we achieve enhanced defense capabilities and promote high interpretability of DNNs. We evaluate the effectiveness of J-SIGR across various architectures by subjecting it to powerful adversarial attacks. Our experimental evaluations provide compelling evidence of the efficacy of J-SIGR against transferred adversarial attacks, while preserving interpretability. The project code can be found at https://github.com/Lywu-github/jJ-SIGR.git. |
|---|---|
| Keywords: |
Selective input gradient regularization, Jacobian normalization, Adversarial robustness |
| College: |
Faculty of Science and Engineering |
| Funders: |
This work was partially supported by NSFC U19A2073 , 62002096, 62001394, 62372150, 62176086. |
| Start Page: |
109902 |