Page 7 - Deep Neural Networks News Today : Breaking News, Live Updates & Top Stories | Vimarsana

Deep neural networks excel at solving intuitive tasks that are hard to describe formally, such as classification, but are easily deceived by maliciously crafted samples, leading to misclassification. Recently, it has been observed that the attack-specific robustness of models obtained through adversarial training does not generalize well to novel or unseen attacks. While data augmentation through mixup in the input space has been shown to improve the generalization and robustness of models, there has been limited research progress on mixup in the latent space. Furthermore, almost no research on mixup has considered the robustness of models against emerging on-manifold adversarial attacks. In this paper, we first design a latent-space data augmentation strategy called dual-mode manifold interpolation, which allows for interpolating disentangled representations of source samples in two modes: convex mixing and binary mask mixing, to synthesize semantic samples. We then propose a resilien

Latentrepresentationmixup larepmixupAdversarial attackAdversarial robustnessDeep neural networksRepresentation learning