Adversarial training with informed data selection
With the increasing amount of available data and advances in computing capabilities, deep neural networks (DNNs) have been successfully employed to solve challenging tasks in various areas, including healthcare, climate, and finance. Nevertheless, state-of-the-art DNNs are susceptible to quasi-imperceptible perturbed versions of the original images -- adversarial examples. These perturbations of the network input can lead to disastrous implications in critical areas where wrong decisions can directly affect human lives. Adversarial training is the most efficient solution to defend the network against these malicious attacks. However, adversarial trained networks generally come with lower clean accuracy and higher computational complexity. This work proposes a data selection (DS) strategy to be applied in the mini-batch training. Based on the cross-entropy loss, the most relevant samples in the batch are selected to update the model parameters in the backpropagation. The simulation results show that a good compromise can be obtained regarding robustness and standard accuracy, whereas the computational complexity of the backpropagation pass is reduced.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Scaling Adversarial Training via Data Selection
Projected Gradient Descent (PGD) is a strong and widely used first-order adversarial attack, yet its computational cost scales poorly, as all training samples undergo identical iterative inner-loop optimization despite c…
Adversarial RobustnessAdversarial AttackTournament Informed Adversarial Quality Diversity
Quality diversity (QD) is a branch of evolutionary computation that seeks high-quality and behaviorally diverse solutions to a problem. While adversarial problems are common, classical QD cannot be easily applied to them…
AdRo-FL: Informed and Secure Client Selection for Federated Learning in the Presence of Adversarial Aggregator
Federated Learning (FL) enables collaborative learning without exposing clients' data. While clients only share model updates with the aggregator, studies reveal that aggregators can infer sensitive information from thes…
Federated LearningPrivacy PreservingContrast-Informed Augmentation and Domain-Adversarial Training for Adult-to-Neonatal MR Reconstruction Generalization
Purpose: To investigate whether contrast-informed data augmentation and domain-adversarial training improve the adult-to-neonatal generalization of the E2E-VarNet. Methods: Three training regimes were investigated: (1) a…
Data AugmentationFriendly Training: Neural Networks Can Adapt Data To Make Learning Easier
In the last decade, motivated by the success of Deep Learning, the scientific community proposed several approaches to make the learning procedure of Neural Networks more effective. When focussing on the way in which the…