Name
Title | ||
|---|---|---|
Regularizer to Mitigate Gradient Masking Effect During Single-Step Adversarial Training |
Abstract | ||
|---|---|---|
Neural networks are susceptible to adversarial samples: samples with imperceptible noise, crafted to manipulate network's prediction. In order to learn robust models, a training procedure, called Adversarial Training has been introduced. During adversarial training, models are trained with mini-batch containing adversarial samples. In order to scale adversarial training for large datasets and networks, fast and simple methods (e.g., FGSM:Fast Gradient Sign Method) of generating adversarial samples are used while training. It has been shown that models trained using single-step adversarial training methods (i.e., adversarial samples generated using non-iterative methods such as FGSM) are not robust, instead they learn to generate weaker adversaries by masking the gradients. In this work, we propose a regularization term in the training loss, to mitigate the effect of gradient masking during single-step adversarial training. The proposed regularization term causes training loss to increase when the distance between logits (i.e., pre-softmax output of a classifier) for FGSM and R-FGSM (small random noise is added to the clean sample before computing its FGSM sample) adversaries of a clean sample becomes large. The proposed single-step adversarial training is faster than computationally expensive state-of-the-art PGD adversarial training method, and also achieves on par results. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/CVPRW.2019.00014 | 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) |
Keywords | DocType | ISSN |
training procedure,adversarial samples,fast gradient sign method,single-step adversarial training methods,training loss,gradient masking effect mitigation,random noise,R-FGSM,neural networks,imperceptible noise | Conference | 2160-7508 |
ISBN | Citations | PageRank |
978-1-7281-2507-7 | 1 | 0.40 |
References | Authors | |
5 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| S. Vivek B. | 1 | 1 | 1.41 |
| Baburaj, Arya | 2 | 1 | 1.07 |
| R. Venkatesh Babu | 3 | 1046 | 84.83 |