activity
20172021
most citedCoverage Testing of Deep Learning Models using Dataset Characterization

15 citations · 22 across the 5 of their papers we have counts for

collaborators

9 papers

cs.SE20214 cited

Graph Neural Network to Dilute Outliers for Refactoring Monolith Application

Utkarsh Desai, Sambaran Bandyopadhyay, Srikanth Tamilselvam

Microservices are becoming the defacto design choice for software architecture. It involves partitioning the software components into finer modules such that the development can ha…

cs.AI20202 cited

Adversarial Black-Box Attacks On Text Classifiers Using Multi-Objective Genetic Optimization Guided By Deep Networks

Alex Mathai, Shreya Khare, Srikanth Tamilselvam +1

We propose a novel genetic-algorithm technique that generates black-box adversarial examples which successfully fool neural network based text classifiers. We perform a genetic sea…

cs.SE2020

Evaluation of Siamese Networks for Semantic Code Search

Raunak Sinha, Utkarsh Desai, Srikanth Tamilselvam +1

With the increase in the number of open repositories and discussion forums, the use of natural language for semantic code search has become increasingly common. The accuracy of the…

cs.CL20201 cited

Benchmarking Popular Classification Models' Robustness to Random and Targeted Corruptions

Utkarsh Desai, Srikanth Tamilselvam, Jassimran Kaur +2

Text classification models, especially neural networks based models, have reached very high accuracy on many popular benchmark datasets. Yet, such models when deployed in real worl…

cs.LG201915 cited

Coverage Testing of Deep Learning Models using Dataset Characterization

Senthil Mani, Anush Sankaran, Srikanth Tamilselvam +1

Deep Neural Networks (DNNs), with its promising performance, are being increasingly used in safety critical applications such as autonomous driving, cancer detection, and secure au…

cs.LG2019

"You might also like this model": Data Driven Approach for Recommending Deep Learning Models for Unknown Image Datasets

Ameya Prabhu, Riddhiman Dasgupta, Anush Sankaran +2

For an unknown (new) classification dataset, choosing an appropriate deep learning architecture is often a recursive, time-taking, and laborious process. In this research, we propo…