One radish, One hole: Specific adversarial training for enhancing neural network’s robustness
Autor: | Xiaoming Huang, Guowen Xu, Shuai Yuan, Yun Zhang, Hongwei Li |
---|---|
Rok vydání: | 2021 |
Předmět: |
Artificial neural network
Computer Networks and Communications Computer science business.industry 05 social sciences Training (meteorology) Process (computing) 010501 environmental sciences Machine learning computer.software_genre 01 natural sciences Adversarial system Robustness (computer science) 0502 economics and business Decision boundary Point (geometry) Artificial intelligence 050207 economics business Computer communication networks computer Software 0105 earth and related environmental sciences |
Zdroj: | Peer-to-Peer Networking and Applications. 14:2262-2274 |
ISSN: | 1936-6450 1936-6442 |
Popis: | Adversarial training has become one of the most widely used methods to defense the attack of adversarial examples, since its properties of improving the robustness of neural networks. To achieve this, many representative works have been proposed to optimize the hyper-parameters in the adversarial training, so as to obtain the optimal trade-off between model classification accuracy and robustness. However, existing works are still in its infancy, especially in terms of model accuracy and training efficiency. In this paper, we propose Specific Adversarial Training(SAT), a novel framework to solve this challenge. Specifically, SAT improves the process of adversarial training by crafting specific perturbation and label for each data point. With this, these generated samples can close and properly cross the decision boundary meanwhile obtain an ideal label, which performs a positive effects in adversarial training. Experimental results show that our method can achieve 88.62% natural accuracy while the adversarial accuracy also improve from 43.79% to 52.34% in the CIFAR-10 dataset. Meanwhile, we achieve a higher efficiency compared to prior works. |
Databáze: | OpenAIRE |
Externí odkaz: |