activity
20172023
most citedHarnessing the Vulnerability of Latent Layers in Adversarially Trained Models

23 citations · 58 across the 35 of their papers we have counts for

collaborators
Showing 2019Show all

8 papers · 1 filter

cs.CV2019

Explain Your Move: Understanding Agent Actions Using Specific and Relevant Feature Attribution

Nikaash Puri, Sukriti Verma, Piyush Gupta +4

As deep reinforcement learning (RL) is applied to more tasks, there is a need to visualize and understand the behavior of learned agents. Saliency maps explain agent behavior by hi…

cs.LG2019★ 5 cited

A Method for Computing Class-wise Universal Adversarial Perturbations

Tejus Gupta, Abhishek Sinha, Nupur Kumari +2

We present an algorithm for computing class-specific universal adversarial perturbations for deep neural networks. Such perturbations can induce misclassification in a large fracti…

cs.CV2019

Attributional Robustness Training using Input-Gradient Spatial Alignment

Mayank Singh, Nupur Kumari, Puneet Mangla +3

Interpretability is an emerging area of research in trustworthy machine learning. Safe deployment of machine learning system mandates that the prediction and its explanation be rel…

cs.CV2019

Document Structure Extraction using Prior based High Resolution Hierarchical Semantic Segmentation

Mausoom Sarkar, Milan Aggarwal, Arneh Jain +2

Structure extraction from document images has been a long-standing research topic due to its high impact on a wide range of practical applications. In this paper, we share our find…

cs.ET2019

OpticalGAN : Generative Adversarial Networks for Continuous Variable Quantum Computation

Nilay Shrivastava, Nikaash Puri, Piyush Gupta +2

We present OpticalGAN, an extension of quantum generative adversarial networks for continuous-variable quantum computation. OpticalGAN consists of photonic variational circuits com…

cs.LG2019

Charting the Right Manifold: Manifold Mixup for Few-shot Learning

Puneet Mangla, Mayank Singh, Abhishek Sinha +3

Few-shot learning algorithms aim to learn model parameters capable of adapting to unseen classes with the help of only a few labeled examples. A recent regularization technique - M…