November 7, 2021

Day

Byzantine Fault-Tolerance in Distributed Computing

Byzantine fault-tolerance lies at the heart of all secure distributed computing. Byzantine faults are used to model nodes in a network that can behave arbitrarily or maliciously. Furthermore, Byzantine nodes can collude among themselves to thwart any distributed protocol. Since the early 80s, there’s been a long line of research in trying to design algorithms...
Read More

On health data architecture design

Authors: Prashant Agrawal, Subodh Sharma, Ambuj Sagar, Subhashis Banerjee
Venue: Book chapter in forthcoming book edited by Smriti Parsheera. Harper Collins. 2021.
Link: https://www.cse.iitd.ac.in/~suban/reports/ndhm2.pdf
Read More

An operational architecture for privacy-by-design in large public service applications

Authors: Prashant Agrawal, Subodh sharma, Subhashis Banerjee.
Venue: Working paper, 2020.
Read More

Privacy concerns with Aadhaar

Authors: Subhashis Banerjee, Subodh Sharma
Venue: Commun. ACM 62(11): 80, 2019
Link: https://cacm.acm.org/magazines/2019/11/240384-privacy-concerns-with-aadhaar/fulltext
Read More

Privacy and Security of Aadhaar: A Computer Science Perspective

Authors: Shweta Agrawal, Subhashis Banerjee and Subodh Sharma
Venue: Economic and Political Weekly, September 2017
Link: https://www.epw.in/journal/2017/37/special-articles/privacy-and-security-aadhaar.html
Read More

Simultaneous Localisation and Mapping (SLAM) and Ego-motion

We briefly looked at some problems related to self-driving cars, in particular that of monocular SLAM and ego-motion. Batch based Monocular SLAM for Egocentric Videos. Suvam Patra, Kartikeya Gupta, Faran Ahmad, Chetan Arora, Subhashis Banerjee.  IEEE Winter Conference on Applications of Computer Vision (WACV), March 2019. (https://arxiv.org/abs/1707.05564,Video 1,Video 2) A Joint 3D-2D based method for free...
Read More

Predicting development indicators using satellite imagery

We develop a set of machine learning based tools for accurate prediction of socio-economic indicators from daytime satellite imagery. The diverse set of indicators are often not intuitively related to observable features in satellite images, and are not even always well correlated with each other. Our predictive tool is more accurate than using night light...
Read More

Reliability of machine learning

We investigate reliability issues of machine learning, especially with respect to adversarial attacks. REGroup: Rank-aggregating Ensemble of Generative Classifiers for Robust Predictions. Lokender Tiwari, Anish Madan, Saket Anand, Subhashis Banerjee.  IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022. (https://openaccess.thecvf.com/content/WACV2022/papers/Tiwari_REGroup_Rank-Aggregating_Ensemble_of_Generative_Classifiers_for_Robust_Predictions_WACV_2022_paper.pdf)
Read More

On large-scale 3D reconstruction

We look at large scale (city scale) 3D reconstruction from image collections. Divide and Conquer: A Hierarchical Approach to Large-scale Structure-from-Motion. Brojeshwar Bhowmick, Suvam Patra, Avishek Chatterjee, Venu Madhav Govindu, Subhashis Banerjee. Computer Vision and Image Understanding (CVIU), April 2017. (http://www.sciencedirect.com/science/article/pii/S1077314217300346, Video)
Read More

1 2 3
We are using cookies to give you the best experience. You can find out more about which cookies we are using or switch them off in privacy settings.
AcceptPrivacy Settings