activity
20172026
most citedHarnessing the Vulnerability of Latent Layers in Adversarially Trained Models

23 citations · 69 across the 30 of their papers we have counts for

collaborators
Showing 2019Show all

10 papers · 1 filter

cs.SI2019

Analysis of Reference and Citation Copying in Evolving Bibliographic Networks

Pradumn Kumar Pandey, Mayank Singh, Pawan Goyal +2

Extensive literature demonstrates how the copying of references (links) can lead to the emergence of various structural properties (e.g., power-law degree distribution and bipartit…

cs.LG20195 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.LG20194 cited

Weakly-Supervised Deep Learning for Domain Invariant Sentiment Classification

Pratik Kayal, Mayank Singh, Pawan Goyal

The task of learning a sentiment classification model that adapts well to any target domain, different from the source domain, is a challenging problem. Majority of the existing ap…

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.SD2019

Improving Voice Separation by Incorporating End-to-end Speech Recognition

Naoya Takahashi, Mayank Kumar Singh, Sakya Basak +3

Despite recent advances in voice separation methods, many challenges remain in realistic scenarios such as noisy recording and the limits of available data. In this work, we propos…

cs.DL2019

The rise and rise of interdisciplinary research: Understanding the interaction dynamics of three major fields -- Physics, Mathematics & Computer Science

Rima Hazra, Mayank Singh, Pawan Goyal +2

The distinction between sciences is becoming increasingly more artificial -- an approach from one area can be easily applied to the other. More exciting research nowadays is happen…