Augmenting Model Robustness with Transformation-Invariant Attacks
The vulnerability of neural networks under adversarial attacks has raised serious concerns and motivated extensive research. It has been shown that both neural networks and adversarial attacks against them can be sensitive to input transformations such as linear translation and rotation, and that human vision, which is robust against adversarial attacks, is invariant to natural input transformations. Based on these, this paper tests the hypothesis that model robustness can be further improved when it is adversarially trained against transformed attacks and transformation-invariant attacks. Experiments on MNIST, CIFAR-10, and restricted ImageNet show that while transformations of attacks alone do not affect robustness, transformation-invariant attacks can improve model robustness by 2.5\% on MNIST, 3.7\% on CIFAR-10, and 1.1\% on restricted ImageNet. We discuss the intuition behind this phenomenon.
Code (0)
등록된 구현이 없습니다.
Tasks
Image CroppingmodelTranslationSimilar Papers 제목 키워드 기반
Improving the Robustness of Adversarial Attacks Using an Affine-Invariant Gradient Estimator
As designers of artificial intelligence try to outwit hackers, both sides continue to hone in on AI's inherent vulnerabilities. Designed and trained from certain statistical distributions of data, AI's deep neural networ…
Adversarial AttackImproving Robustness of Facial Landmark Detection by Defending Against Adversarial Attacks
Many recent developments in facial landmark detection have been driven by stacking model parameters or augmenting annotations. However, three subsequent challenges remain, including 1) an increase in computational ov…
Face AlignmentFacial Landmark DetectionTraining or Architecture? How to Incorporate Invariance in Neural Networks
Many applications require the robustness, or ideally the invariance, of a neural network to certain transformations of input data. Most commonly, this requirement is addressed by either augmenting the training data, usin…
3D Point Cloud ClassificationComputational EfficiencyPoint Cloud ClassificationTargeted View-Invariant Adversarial Perturbations for 3D Object Recognition
Adversarial attacks pose significant challenges in 3D object recognition, especially in scenarios involving multi-view analysis where objects can be observed from varying angles. This paper introduces View-Invariant Adve…
3D Object RecognitionAdversarial RobustnessObject RecognitionRobustness to Transformations Across Categories: Is Robustness To Transformations Driven by Invariant Neural Representations?
Deep Convolutional Neural Networks (DCNNs) have demonstrated impressive robustness to recognize objects under transformations (eg. blur or noise) when these transformations are included in the training set. A hypothesis …