Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
10-2018
Abstract
Deep Neural Networks (DNNs) have been shown to be vulnerable against adversarial examples, which are data points cleverly constructed to fool the classifier. Such attacks can be devastating in practice, especially as DNNs are being applied to ever increasing critical tasks like image recognition in autonomous driving. In this paper, we introduce a new perspective on the problem. We do so by first defining robustness of a classifier to adversarial exploitation. Next, we show that the problem of adversarial example generation can be posed as learning problem. We also categorize attacks in literature into high and low perturbation attacks; well-known attacks like FGSM [11] and our attack produce higher perturbation adversarial examples while the more potent but computationally inefficient Carlini-Wagner [5] (CW) attack is low perturbation. Next, we show that the dual approach of the attack learning problem can be used as a defensive technique that is effective against high perturbation attacks. Finally, we show that a classifier masking method achieved by adding noise to the a neural network’s logit output protects against low distortion attacks such as the CW attack. We also show that both our learning and masking defense can work simultaneously to protect against multiple attacks. We demonstrate the efficacy of our techniques by experimenting with the MNIST and CIFAR-10 datasets.
Keywords
adversarial examples, robust learning
Discipline
Databases and Information Systems | Software Engineering
Research Areas
Data Science and Engineering
Publication
Proceedings of the 9th Conference on Decision and Game Theory for Security: GameSec 2018, Seattle, USA, October 29-31
Volume
11199
First Page
453
Last Page
464
ISBN
978-3-030-01553-4
Identifier
10.1007/978-3-030-01554-1_26
Publisher
Springer Link
City or Country
Seattle, USA
Citation
NGUYEN, Linh; WANG, Sky; and SINHA, Arunesh.
A learning and masking approach to secure learning. (2018). Proceedings of the 9th Conference on Decision and Game Theory for Security: GameSec 2018, Seattle, USA, October 29-31. 11199, 453-464.
Available at: https://ink.library.smu.edu.sg/sis_research/4793
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1007/978-3-030-01554-1_26