1

Certified Robustness in Federated Learning

We assess the certified robustness of models trained in a federated fashion.

Data Dependent Randomized Smoothing

We optimize the smoothing parameters per input point in randomized smoothing.

3DeformRS: Certifying Spatial Deformations on Point Clouds

We design the anti-adversary layer that enhances the robustness of pretrained models against strong adversarial attacks.

Combating Adversaries with Anti-Adversaries

We design the anti-adversary layer that enhances the robustness of pretrained models against strong adversarial attacks.

DeformRS: Certifying Input Deformations with Randomized Smoothing

We extend randomized smoothing to certify image deformations such as rotation, translation, scaling, and affine.

Rethinking Clustering for Robustness

We analyze the effect of encouraging the learnt features from DNN to be more semantically meaningful through clustering on the PGD-Robustness of the DNN.

Enhancing Adversarial Robustness via Test-time Transformation Ensembling

We leverage test time augmentation for enhancing both empirical and certified robustness of DNNs.

Gabor Layers Enhance Network Robustness

We replace the first convolutional layer in deep neural networks with a Gabor layer to enhance networks robustness.

Adaptive Learning of the Optimal Batch Size of SGD

We desaign an algorithm that adaptively adjusts the batch size for SGD.