Adaptive Image Reconstruction for Defense Against Adversarial Attacks
Document Type
Article
Publication Date
9-30-2022
Abstract
Adversarial attacks can fool convolutional networks and make the systems vulnerable to fraud and deception. How to defend against malicious attacks is a critical challenge in practice. Adversarial attacks are often conducted by adding tiny perturbations on images to cause network misclassification. Noise reduction can defend the attacks; however, it is not suited for all the cases. Considering that different models have different tolerance abilities on adversarial attacks, we develop a novel detecting module to remove noise by adaptive process and detect adversarial attacks without modifying the models. Experimental results show that by comparing the classification results on adversarial samples of MNIST and two subclasses of ImageNet datasets, our models can successfully remove most of the noise and obtain detection accuracies of 97.71% and 92.96%, respectively. Furthermore, our adaptive module can be assembled into different networks to achieve detection accuracies of 70.83% and 71.96%, respectively, on the white-box adversarial attacks of ResNet18 and SCD01MLP images. The best accuracy of 62.5% is obtained for both networks when dealing with the black-box attacks.
Identifier
85137382912 (Scopus)
Publication Title
International Journal of Pattern Recognition and Artificial Intelligence
External Full Text Location
https://doi.org/10.1142/S021800142252022X
ISSN
02180014
Issue
12
Volume
36
Recommended Citation
Yang, Yanan; Shih, Frank Y.; and Chang, I. Cheng, "Adaptive Image Reconstruction for Defense Against Adversarial Attacks" (2022). Faculty Publications. 2643.
https://digitalcommons.njit.edu/fac_pubs/2643