12 citations · 33 across the 15 of their papers we have counts for
4 papers · 1 filter
How do SGD hyperparameters in natural training affect adversarial robustness?
Sandesh Kamath, Amit Deshpande, K V Subrahmanyam
Learning rate, batch size and momentum are three important hyperparameters in the SGD algorithm. It is known from the work of Jastrzebski et al. arXiv:1711.04623 that large batch s…
On Universalized Adversarial and Invariant Perturbations
Sandesh Kamath, Amit Deshpande, K V Subrahmanyam
Convolutional neural networks or standard CNNs (StdCNNs) are translation-equivariant models that achieve translation invariance when trained on data augmented with sufficient trans…
Universalization of any adversarial attack using very few test examples
Sandesh Kamath, Amit Deshpande, K V Subrahmanyam +1
Deep learning models are known to be vulnerable not only to input-dependent adversarial attacks but also to input-agnostic or universal adversarial attacks. Dezfooli et al. \cite{D…
Can we have it all? On the Trade-off between Spatial and Adversarial Robustness of Neural Networks
Sandesh Kamath, Amit Deshpande, K V Subrahmanyam +1
(Non-)robustness of neural networks to small, adversarial pixel-wise perturbations, and as more recently shown, to even random spatial transformations (e.g., translations, rotation…