3 citations · 5 across the 8 of their papers we have counts for
8 papers
Are You Thinking What I am Thinking? : Examining Conceptual Separation in Neural Architectures
Jaee Ponde, Roshni Agarwal, Subhashis Banerjee
Neural networks are increasingly employed to identify both well-defined and ambiguous concepts, yet output-level metrics reveal little about how those concepts are represented inte…
Validity, Reliability, and Transparency in Artificial Intelligence Regulation
A. Mukundan, Debayan Gupta, Subhashis Banerjee
AI systems increasingly produce claims about people that shape access to employment, healthcare, and other consequential services. Yet lawful data processing and predictive accurac…
A New Framework to Analyse the Distributional Robustness of Deep Neural Networks
Divij Khaitan, Subhashis Banerjee
Deep neural networks have achieved impressive performance on a variety of tasks, but their brittleness to distributional shifts remains a significant barrier to real-world deployme…
Traceable mixnets
Prashant Agrawal, Abhinav Nakarmi, Mahavir Prasad Jhawar +2
We introduce the notion of \emph{traceable mixnets}. In a traditional mixnet, multiple mix-servers jointly permute and decrypt a list of ciphertexts to produce a list of plaintexts…
From Forks to Forceps: A New Framework for Instance Segmentation of Surgical Instruments
Britty Baby, Daksh Thapar, Mustafa Chasmai +5
Minimally invasive surgeries and related applications demand surgical tool classification and segmentation at the instance level. Surgical tools are similar in appearance and are l…
Ballot stuffing and participation privacy in pollsite voting
Prashant Agrawal, Abhinav Nakarmi, Mahabir Prasad Jhanwar +2
We study the problem of simultaneously addressing both ballot stuffing and participation privacy for pollsite voting systems. Ballot stuffing is the attack where fake ballots (not…
Measuring poverty in India with machine learning and remote sensing
Adel Daoud, Felipe Jordan, Makkunda Sharma +4
In this paper, we use deep learning to estimate living conditions in India. We use both census and surveys to train the models. Our procedure achieves comparable results to those f…
REGroup: Rank-aggregating Ensemble of Generative Classifiers for Robust Predictions
Lokender Tiwari, Anish Madan, Saket Anand +1
Deep Neural Networks (DNNs) are often criticized for being susceptible to adversarial attacks. Most successful defense strategies adopt adversarial training or random input transfo…