1.8k citations · 2.6k across the 22 of their papers we have counts for
7 papers · 1 filter
Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICA
Sébastien Lachapelle, Pau Rodríguez López, Yash Sharma +4
This work introduces a novel principle we call disentanglement via mechanism sparsity regularization, which can be applied when the latent factors of interest depend sparsely on pa…
Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style
Julius von Kügelgen, Yash Sharma, Luigi Gresele +4
Self-supervised representation learning has shown remarkable success in a number of domains. A common practice is to perform data augmentation via hand-crafted transformations inte…
Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding
David Klindt, Lukas Schott, Yash Sharma +4
We construct an unsupervised learning model that achieves nonlinear disentanglement of underlying factors of variation in naturalistic videos. Previous work suggests that represent…
Bypassing Feature Squeezing by Increasing Adversary Strength
Yash Sharma, Pin-Yu Chen
Feature Squeezing is a recently proposed defense method which reduces the search space available to an adversary by coalescing samples that correspond to many different feature vec…
Attacking the Madry Defense Model with -based Adversarial Examples
Yash Sharma, Pin-Yu Chen
The Madry Lab recently hosted a competition designed to test the robustness of their adversarially trained MNIST model. Attacks were constrained to perturb each pixel of the input…
EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples
Pin-Yu Chen, Yash Sharma, Huan Zhang +2
Recent studies have highlighted the vulnerability of deep neural networks (DNNs) to adversarial examples - a visually indistinguishable adversarial image can easily be crafted to c…
ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
Pin-Yu Chen, Huan Zhang, Yash Sharma +2
Deep neural networks (DNNs) are one of the most prominent technologies of our time, as they achieve state-of-the-art performance in many machine learning tasks, including but not l…