TY - GEN
T1 - Parametric noise injection
T2 - 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
AU - He, Zhezhi
AU - Rakin, Adnan Siraj
AU - Fan, Deliang
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/6
Y1 - 2019/6
N2 - Recent developments in the field of Deep Learning have exposed the underlying vulnerability of Deep Neural Network (DNN) against adversarial examples. In image classification, an adversarial example is a carefully modified image that is visually imperceptible to the original image but can cause DNN model to misclassify it. Training the network with Gaussian noise is an effective technique to perform model regularization, thus improving model robustness against input variation. Inspired by this classical method, we explore to utilize the regularization characteristic of noise injection to improve DNN's robustness against adversarial attack. In this work, we propose Parametric-Noise-Injection (PNI) which involves trainable Gaussian noise injection at each layer on either activation or weights through solving the Min-Max optimization problem, embedded with adversarial training. These parameters are trained explicitly to achieve improved robustness. The extensive results show that our proposed PNI technique effectively improves the robustness against a variety of powerful white-box and black-box attacks such as PGD, C&W, FGSM, transferable attack, and ZOO attack. Last but not the least, PNI method improves both clean-and perturbed-data accuracy, in comparison to the state-of-the-art defense methods, which outperforms current unbroken PGD defense by 1.1% and 6.8% on clean-and perturbed-test data respectively, using ResNet-20 architecture.
AB - Recent developments in the field of Deep Learning have exposed the underlying vulnerability of Deep Neural Network (DNN) against adversarial examples. In image classification, an adversarial example is a carefully modified image that is visually imperceptible to the original image but can cause DNN model to misclassify it. Training the network with Gaussian noise is an effective technique to perform model regularization, thus improving model robustness against input variation. Inspired by this classical method, we explore to utilize the regularization characteristic of noise injection to improve DNN's robustness against adversarial attack. In this work, we propose Parametric-Noise-Injection (PNI) which involves trainable Gaussian noise injection at each layer on either activation or weights through solving the Min-Max optimization problem, embedded with adversarial training. These parameters are trained explicitly to achieve improved robustness. The extensive results show that our proposed PNI technique effectively improves the robustness against a variety of powerful white-box and black-box attacks such as PGD, C&W, FGSM, transferable attack, and ZOO attack. Last but not the least, PNI method improves both clean-and perturbed-data accuracy, in comparison to the state-of-the-art defense methods, which outperforms current unbroken PGD defense by 1.1% and 6.8% on clean-and perturbed-test data respectively, using ResNet-20 architecture.
KW - Categorization
KW - Deep Learning
KW - Optimization Methods
KW - Recognition: Detection
KW - Retrieval
UR - http://www.scopus.com/inward/record.url?scp=85078789954&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85078789954&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2019.00068
DO - 10.1109/CVPR.2019.00068
M3 - Conference contribution
AN - SCOPUS:85078789954
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 588
EP - 597
BT - Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
PB - IEEE Computer Society
Y2 - 16 June 2019 through 20 June 2019
ER -