activity
20162022
most citedUPSET and ANGRI : Breaking High Performance Image Classifiers

91 citations · 296 across the 23 of their papers we have counts for

collaborators
Showing cs.LGShow all

7 papers · 1 filter

cs.LG20211 cited

Identification of Attack-Specific Signatures in Adversarial Examples

Hossein Souri, Pirazh Khorramshahi, Chun Pong Lau +2

The adversarial attack literature contains a myriad of algorithms for crafting perturbations which yield pathological behavior in neural networks. In many cases, multiple algorithm…

cs.LG20211 cited

To Boost or not to Boost: On the Limits of Boosted Neural Networks

Sai Saketh Rambhatla, Michael Jones, Rama Chellappa

Boosting is a method for finding a highly accurate hypothesis by linearly combining many ``weak" hypotheses, each of which may be only moderately accurate. Thus, boosting is a meth…

cs.LG2019

cGANs with Multi-Hinge Loss

Ilya Kavalerov, Wojciech Czaja, Rama Chellappa

We propose a new algorithm to incorporate class conditional information into the critic of GANs via a multi-class generalization of the commonly used Hinge loss that is compatible…

cs.LG20198 cited

Invert and Defend: Model-based Approximate Inversion of Generative Adversarial Networks for Secure Inference

Wei-An Lin, Yogesh Balaji, Pouya Samangouei +1

Inferring the latent variable generating a given test sample is a challenging problem in Generative Adversarial Networks (GANs). In this paper, we propose InvGAN - a novel framewor…

cs.LG2019

Normalized Wasserstein Distance for Mixture Distributions with Applications in Adversarial Learning and Domain Adaptation

Yogesh Balaji, Rama Chellappa, Soheil Feizi

Understanding proper distance measures between distributions is at the core of several learning tasks such as generative models, domain adaptation, clustering, etc. In this work, w…

cs.LG2018

Entropic GANs meet VAEs: A Statistical Approach to Compute Sample Likelihoods in GANs

Yogesh Balaji, Hamed Hassani, Rama Chellappa +1

Building on the success of deep learning, two modern approaches to learn a probability model from the data are Generative Adversarial Networks (GANs) and Variational AutoEncoders (…