arXiv subjects

Abhishek Singh

Publications and source records attributed to Abhishek Singh.

At least 55 records · Page 3Linked to original sources

arXiv2022

Decouple-and-Sample: Protecting sensitive information in task agnostic data release

We propose sanitizer, a framework for secure and task-agnostic data release. While releasing datasets continues to make a big impact in various applications of computer vision, its impact is mostly realized when data sharing is not inhibited by privacy concerns. We alleviate these concerns by sanitizing datasets in a two-stage process. First, we introduce a global decoupling stage for decomposing raw data into sensitive and non-sensitive latent representations. Secondly, we design a local sampling stage to synthetically generate sensitive information with differential privacy and merge it with non-sensitive latent features to create a useful representation while preserving the privacy. This newly formed latent information is a task-agnostic representation of the original dataset with anonymized sensitive information. While most algorithms sanitize data in a task-dependent manner, a few task-agnostic sanitization techniques sanitize data by censoring sensitive information. In this work, we show that a better privacy-utility trade-off is achieved if sensitive information can be synthesized privately. We validate the effectiveness of the sanitizer by outperforming state-of-the-art baselines on the existing benchmark tasks and demonstrating tasks that are not possible using existing techniques.

cs.CR↗

arXiv2022

Singularity: Planet-Scale, Preemptive and Elastic Scheduling of AI Workloads

Lowering costs by driving high utilization across deep learning workloads is a crucial lever for cloud providers. We present Singularity, Microsoft's globally distributed scheduling service for highly-efficient and reliable execution of deep learning training and inference workloads. At the heart of Singularity is a novel, workload-aware scheduler that can transparently preempt and elastically scale deep learning workloads to drive high utilization without impacting their correctness or performance, across a global fleet of AI accelerators (e.g., GPUs, FPGAs). All jobs in Singularity are preemptable, migratable, and dynamically resizable (elastic) by default: a live job can be dynamically and transparently (a) preempted and migrated to a different set of nodes, cluster, data center or a region and resumed exactly from the point where the execution was preempted, and (b) resized (i.e., elastically scaled-up/down) on a varying set of accelerators of a given type. Our mechanisms are transparent in that they do not require the user to make any changes to their code or require using any custom libraries that may limit flexibility. Additionally, our approach significantly improves the reliability of deep learning workloads. We show that the resulting efficiency and reliability gains with Singularity are achieved with negligible impact on the steady-state performance. Finally, our design approach is agnostic of DNN architectures and handles a variety of parallelism strategies (e.g., data/pipeline/model parallelism).

cs.DC↗

arXiv2022

Paper card-based vs application-based vaccine credentials: a comparison

In this early draft, we provide an overview on similarities and differences in the implementation of a paper card-based vaccine credential system and an app-based vaccine credential system. A vaccine credential's primary goal is to regulate entry and ensure safety of individuals within densely packed public locations and workspaces. This is critical for containing the rapid spread of Covid-19 in densely packed public locations since a single individual can infect a large majority of people in a crowd. A vaccine credential can also provide information such as an individual's Covid-19 vaccination history and adverse symptom reaction history to judge their potential impact on the overall health of individuals within densely packed public locations and workspaces. After completing the comparisons, we believe a card-based implementation will benefit regions with less socioeconomic mobility, limited resources, and stagnant administrations. An app-based implementation on the other hand will benefit regions with equitable internet access and lower technological divide. We also believe an interoperable system of both credential systems will work best for regions with enormous working-class populations and dense housing clusters.

cs.CY↗

arXiv2021

MedPerf: Open Benchmarking Platform for Medical Artificial Intelligence using Federated Evaluation

Medical AI has tremendous potential to advance healthcare by supporting the evidence-based practice of medicine, personalizing patient treatment, reducing costs, and improving provider and patient experience. We argue that unlocking this potential requires a systematic way to measure the performance of medical AI models on large-scale heterogeneous data. To meet this need, we are building MedPerf, an open framework for benchmarking machine learning in the medical domain. MedPerf will enable federated evaluation in which models are securely distributed to different facilities for evaluation, thereby empowering healthcare organizations to assess and verify the performance of AI models in an efficient and human-supervised process, while prioritizing privacy. We describe the current challenges healthcare and AI communities face, the need for an open platform, the design philosophy of MedPerf, its current implementation status, and our roadmap. We call for researchers and organizations to join us in creating the MedPerf open benchmarking platform.

cs.LG↗

arXiv2021

AdaSplit: Adaptive Trade-offs for Resource-constrained Distributed Deep Learning

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.

cs.LG↗

arXiv2021

Tunable cryogenic THz cavity for strong light-matter coupling in complex materials

We report here the realization and commissioning of an experiment dedicated to the study of the optical properties of light matter hybrids constituted of crystalline samples embedded in an optical cavity. The experimental assembly developed offers the unique opportunity to study the weak and strong coupling regime between a tunable optical cavity in cryogenic environment and low energy degrees of freedom such as phonons, magnons or charge fluctuations. We describe here the setup developed which allows the positioning of crystalline samples in an optical cavity of different quality factor, the tuning of the cavity length at cryogenic temperatures and its optical characterization with a broadband time domain THz spectrometer (0.2-6 THz). We demonstrate the versatility of the setup by studying the vibrational strong coupling in CuGeO3 single crystal at cryogenic temperatures.

physics.ins-det↗

arXiv2021

Mobility Data Analysis and Applications: A mid-year 2021 Survey

In this work we review recent works analyzing mobility data and its application in understanding the epidemic dynamics for the COVID-19 pandemic and more. We also discuss privacy-preserving solutions to analyze the mobility data in order to expand its reach towards a wider population.

cs.CY↗

arXiv2021

Vaccination Worldwide: Strategies, Distribution and Challenges

The Coronavirus 2019 (Covid-19) pandemic caused by the SARS-CoV-2 virus represents an unprecedented crisis for our planet. It is a bane of the über connected world that we live in that this virus has affected almost all countries and caused mortality and economic upheaval at a scale whose effects are going to be felt for generations to come. While we can all be buoyed at the pace at which vaccines have been developed and brought to market, there are still challenges ahead for all countries to get their populations vaccinated equitably and effectively. This paper provides an overview of ongoing immunization efforts in various countries. In this early draft, we have identified a few key factors that we use to review different countries' current COVID-19 immunization strategies and their strengths and draw conclusions so that policymakers worldwide can learn from them. Our paper focuses on processes related to vaccine approval, allocation and prioritization, distribution strategies, population to vaccine ratio, vaccination governance, accessibility and use of digital solutions, and government policies. The statistics and numbers are dated as per the draft date [June 24th, 2021].

q-bio.PE↗

arXiv2021

Can Self Reported Symptoms Predict Daily COVID-19 Cases?

The COVID-19 pandemic has impacted lives and economies across the globe, leading to many deaths. While vaccination is an important intervention, its roll-out is slow and unequal across the globe. Therefore, extensive testing still remains one of the key methods to monitor and contain the virus. Testing on a large scale is expensive and arduous. Hence, we need alternate methods to estimate the number of cases. Online surveys have been shown to be an effective method for data collection amidst the pandemic. In this work, we develop machine learning models to estimate the prevalence of COVID-19 using self-reported symptoms. Our best model predicts the daily cases with a mean absolute error (MAE) of 226.30 (normalized MAE of 27.09%) per state, which demonstrates the possibility of predicting the actual number of confirmed cases by utilizing self-reported symptoms. The models are developed at two levels of data granularity - local models, which are trained at the state level, and a single global model which is trained on the combined data aggregated across all states. Our results indicate a lower error on the local models as opposed to the global model. In addition, we also show that the most important symptoms (features) vary considerably from state to state. This work demonstrates that the models developed on crowd-sourced data, curated via online platforms, can complement the existing epidemiological surveillance infrastructure in a cost-effective manner. The code is publicly available at https://github.com/parthpatwa/Can-Self-Reported-Symptoms-Predict-Daily-COVID-19-Cases.

cs.LG↗

arXiv2021

COVID-19 Outbreak Prediction and Analysis using Self Reported Symptoms

It is crucial for policymakers to understand the community prevalence of COVID-19 so combative resources can be effectively allocated and prioritized during the COVID-19 pandemic. Traditionally, community prevalence has been assessed through diagnostic and antibody testing data. However, despite the increasing availability of COVID-19 testing, the required level has not been met in most parts of the globe, introducing a need for an alternative method for communities to determine disease prevalence. This is further complicated by the observation that COVID-19 prevalence and spread varies across different spatial, temporal, and demographics. In this study, we understand trends in the spread of COVID-19 by utilizing the results of self-reported COVID-19 symptoms surveys as an alternative to COVID-19 testing reports. This allows us to assess community disease prevalence, even in areas with low COVID-19 testing ability. Using individually reported symptom data from various populations, our method predicts the likely percentage of the population that tested positive for COVID-19. We do so with a Mean Absolute Error (MAE) of 1.14 and Mean Relative Error (MRE) of 60.40\% with 95\% confidence interval as (60.12, 60.67). This implies that our model predicts +/- 1140 cases than the original in a population of 1 million. In addition, we forecast the location-wise percentage of the population testing positive for the next 30 days using self-reported symptoms data from previous days. The MAE for this method is as low as 0.15 (MRE of 23.61\% with 95\% confidence interval as (23.6, 13.7)) for New York. We present an analysis of these results, exposing various clinical attributes of interest across different demographics. Lastly, we qualitatively analyze how various policy enactments (testing, curfew) affect the prevalence of COVID-19 in a community.

cs.LG↗

arXiv2021

DISCO: Dynamic and Invariant Sensitive Channel Obfuscation for deep neural networks

Recent deep learning models have shown remarkable performance in image classification. While these deep learning systems are getting closer to practical deployment, the common assumption made about data is that it does not carry any sensitive information. This assumption may not hold for many practical cases, especially in the domain where an individual's personal information is involved, like healthcare and facial recognition systems. We posit that selectively removing features in this latent space can protect the sensitive information and provide a better privacy-utility trade-off. Consequently, we propose DISCO which learns a dynamic and data driven pruning filter to selectively obfuscate sensitive information in the feature space. We propose diverse attack schemes for sensitive inputs \& attributes and demonstrate the effectiveness of DISCO against state-of-the-art methods through quantitative and qualitative evaluation. Finally, we also release an evaluation benchmark dataset of 1 million sensitive representations to encourage rigorous exploration of novel attack schemes.

cs.CV↗

arXiv2021

An In-Memory Analog Computing Co-Processor for Energy-Efficient CNN Inference on Mobile Devices

In this paper, we develop an in-memory analog computing (IMAC) architecture realizing both synaptic behavior and activation functions within non-volatile memory arrays. Spin-orbit torque magnetoresistive random-access memory (SOT-MRAM) devices are leveraged to realize sigmoidal neurons as well as binarized synapses. First, it is shown the proposed IMAC architecture can be utilized to realize a multilayer perceptron (MLP) classifier achieving orders of magnitude performance improvement compared to previous mixed-signal and digital implementations. Next, a heterogeneous mixed-signal and mixed-precision CPU-IMAC architecture is proposed for convolutional neural networks (CNNs) inference on mobile processors, in which IMAC is designed as a co-processor to realize fully-connected (FC) layers whereas convolution layers are executed in CPU. Architecture-level analytical models are developed to evaluate the performance and energy consumption of the CPU-IMAC architecture. Simulation results exhibit 6.5% and 10% energy savings for CPU-IMAC based realizations of LeNet and VGG CNN models, for MNIST and CIFAR-10 pattern recognition tasks, respectively.

cs.AR↗

arXiv2021

Automatic calibration of time of flight based non-line-of-sight reconstruction

Time of flight based Non-line-of-sight (NLOS) imaging approaches require precise calibration of illumination and detector positions on the visible scene to produce reasonable results. If this calibration error is sufficiently high, reconstruction can fail entirely without any indication to the user. In this work, we highlight the necessity of building autocalibration into NLOS reconstruction in order to handle mis-calibration. We propose a forward model of NLOS measurements that is differentiable with respect to both, the hidden scene albedo, and virtual illumination and detector positions. With only a mean squared error loss and no regularization, our model enables joint reconstruction and recovery of calibration parameters by minimizing the measurement residual using gradient descent. We demonstrate our method is able to produce robust reconstructions using simulated and real data where the calibration error applied causes other state of the art algorithms to fail.

eess.IV↗

arXiv2021

COVID-19 Tests Gone Rogue: Privacy, Efficacy, Mismanagement and Misunderstandings

COVID-19 testing, the cornerstone for effective screening and identification of COVID-19 cases, remains paramount as an intervention tool to curb the spread of COVID-19 both at local and national levels. However, the speed at which the pandemic struck and the response was rolled out, the widespread impact on healthcare infrastructure, the lack of sufficient preparation within the public health system, and the complexity of the crisis led to utter confusion among test-takers. Invasion of privacy remains a crucial concern. The user experience of test takers remains low. User friction affects user behavior and discourages participation in testing programs. Test efficacy has been overstated. Test results are poorly understood resulting in inappropriate follow-up recommendations. Herein, we review the current landscape of COVID-19 testing, identify four key challenges, and discuss the consequences of the failure to address these challenges. The current infrastructure around testing and information propagation is highly privacy-invasive and does not leverage scalable digital components. In this work, we discuss challenges complicating the existing covid-19 testing ecosystem and highlight the need to improve the testing experience for the user and reduce privacy invasions. Digital tools will play a critical role in resolving these challenges.

cs.CY↗

arXiv2021

Blockchain Based Accounts Payable Platform for Goods Trade

Goods trade is a supply chain transaction that involves shippers buying goods from suppliers and carriers providing goods transportation. Shippers are issued invoices from suppliers and carriers. Shippers carry out goods receiving and invoice processing before payment processing of bills for suppliers and carriers, where invoice processing includes tasks like processing claims and adjusting the bill payments. Goods receiving involves verification of received goods by the Shipper's receiving team. Invoice processing is carried out by the Shipper's accounts payable team, which in turn is verified by the accounts receivable teams of suppliers and carriers. This paper presents a blockchain-based accounts payable system that generates claims for the deficiency in the goods received and accordingly adjusts the payment in the bills for suppliers and carriers. Primary motivations for these supply chain organizations to adopt blockchain-based accounts payable systems are to eliminate the process redundancies (accounts payable vs. accounts receivable), to reduce the number of disputes among the transacting participants, and to accelerate the accounts payable processes via optimizations in the claims generation and blockchain-based dispute reconciliation.

cs.DC↗

arXiv2021

Safepaths: Vaccine Diary Protocol and Decentralized Vaccine Coordination System using a Privacy Preserving User Centric Experience

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.

cs.CR↗

arXiv2021

MIT SafePaths Card (MiSaCa): Augmenting Paper Based Vaccination Cards with Printed Codes

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.

cs.CY↗

arXiv2021

Spatial K-anonymity: A Privacy-preserving Method for COVID-19 Related Geospatial Technologies

There is a growing need for spatial privacy considerations in the many geo-spatial technologies that have been created as solutions for COVID-19-related issues. Although effective geo-spatial technologies have already been rolled out, most have significantly sacrificed privacy for utility. In this paper, we explore spatial k-anonymity, a privacy-preserving method that can address this unnecessary tradeoff by providing the best of both privacy and utility. After evaluating its past implications in geo-spatial use cases, we propose applications of spatial k-anonymity in the data sharing and managing of COVID-19 contact tracing technologies as well as heat maps showing a user's travel history. We then justify our propositions by comparing spatial k-anonymity with several other spatial privacy methods, including differential privacy, geo-indistinguishability, and manual consent based redaction. Our hope is to raise awareness of the ever-growing risks associated with spatial privacy and how they can be solved with Spatial K-anonymity.

cs.CR↗