Abhishek Singh

Ayush Chopra, Surya Kant Sahu, Abhishek Singh et al.

Distributed deep learning frameworks like federated learning (FL) and its variants are enabling personalized experiences across a wide range of web clients and mobile/IoT devices. However, FL-based frameworks are constrained by computational resources at clients due to the exploding growth of model parameters (eg. billion parameter model). Split learning (SL), a recent framework, reduces client compute load by splitting the model training between client and server. This flexibility is extremely useful for low-compute setups but is often achieved at cost of increase in bandwidth consumption and may result in sub-optimal convergence, especially when client data is heterogeneous. In this work, we introduce AdaSplit which enables efficiently scaling SL to low resource scenarios by reducing bandwidth consumption and improving performance across heterogeneous clients. To capture and benchmark this multi-dimensional nature of distributed deep learning, we also introduce C3-Score, a metric to evaluate performance under resource budgets. We validate the effectiveness of AdaSplit under limited resources through extensive experimental comparison with strong federated and split learning baselines. We also present a sensitivity analysis of key design choices in AdaSplit which validates the ability of AdaSplit to provide adaptive trade-offs across variable resource budgets.

Abhishek Singh, Ramesh Raskar, Anna Lysyanskaya

In this early draft, we present an end-to-end decentralized protocol for the secure and privacy preserving workflow of vaccination, vaccination status verification, and adverse reactions or symptoms reporting. The proposed system improves the efficiency, privacy, equity, and effectiveness of the existing manual system while remaining interoperable with its capabilities. We also discuss various security concerns and alternate methodologies based on the proposed protocols.

Joseph Bae, Rohan Sukumaran, Sheshank Shankar et al.

In this early draft, we describe a user-centric, card-based system for vaccine distribution. Our system makes use of digitally signed QR codes and their use for phased vaccine distribution, vaccine administration/record-keeping, immunization verification, and follow-up symptom reporting. Furthermore, we propose and describe a complementary scanner app system to be used by vaccination clinics, public health officials, and immunization verification parties to effectively utilize card-based framework. We believe that the proposed system provides a privacy-preserving and efficient framework for vaccine distribution in both developed and developing regions.

Abhishek Singh, Ramesh Raskar

In the current pandemic, testing continues to be the most important tool for monitoring and curbing the disease spread and early identification of the disease to perform health-related interventions like quarantine, contact tracing and etc. Therefore, the ability to verify the testing status is pertinent as public places prepare to safely open. Recent advances in cryptographic tools have made it possible to build a secure and resilient digital-id system. In this work, we propose to build an end to end COVID-19 results verification protocol that takes privacy, computation, and other practical concerns into account for designing an inter-operable layer of testing results verification system that could potentially enable less stringent and more selective lockdowns. We also discuss various concerns encompassing the security, privacy, ethics and equity aspect of the proposed system.

Sheshank Shankar, Rishank Kanaparti, Ayush Chopra et al.

As we await a vaccine, social-distancing via efficient contact tracing has emerged as the primary health strategy to dampen the spread of COVID-19. To enable efficient digital contact tracing, we present a novel system to estimate pair-wise individual proximity, via a joint model of Bluetooth Low Energy (BLE) signals with other on-device sensors (accelerometer, magnetometer, gyroscope). We explore multiple ways of interpreting the sensor data stream (time-series, histogram, etc) and use several statistical and deep learning methods to learn representations for sensing proximity. We report the normalized Decision Cost Function (nDCF) metric and analyze the differential impact of the various input signals, as well as discuss various challenges associated with this task.