BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Subhankar Mishra

Subhankar Mishra contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Machine LearningCryptography and SecuritySocial and Information NetworksArtificial Intelligencecs.CYeess.SYInformation Retrievalq-fin.GNSystems and ControlComputation and LanguageComputer VisionDistributed, Parallel, and Cluster Computing

Trust snapshot

Quick read

Trust 21 - EmergingVerification L1Unclaimed author
21works
0followers
12topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Identity and collaboration

How to connect with this researcher

Claiming links this public author record to a researcher profile and unlocks direct collaboration workflows.

Log in to claim

Direct collaboration

Open a focused conversation when the fit is right

Claim this author entity first to unlock direct invitations.

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

21 published item(s)

preprint2026arXiv

Clean-GS: Semantic Mask-Guided Pruning for 3D Gaussian Splatting

3D Gaussian Splatting produces high-quality scene reconstructions but generates hundreds of thousands of spurious Gaussians (floaters) scattered throughout the environment. These artifacts obscure objects of interest and inflate model sizes, hindering deployment in bandwidth-constrained applications. We present Clean-GS, a method for removing background clutter and floaters from 3DGS reconstructions using sparse semantic masks. Our approach combines whitelist-based spatial filtering with color-guided validation and outlier removal to achieve 60-80\% model compression while preserving object quality. Unlike existing 3DGS pruning methods that rely on global importance metrics, Clean-GS uses semantic information from as few as 3 segmentation masks (1\% of views) to identify and remove Gaussians not belonging to the target object. Our multi-stage approach consisting of (1) whitelist filtering via projection to masked regions, (2) depth-buffered color validation, and (3) neighbor-based outlier removal isolates monuments and objects from complex outdoor scenes. Experiments on Tanks and Temples show that Clean-GS reduces file sizes from 125MB to 47MB while maintaining rendering quality, making 3DGS models practical for web deployment and AR/VR applications. Our code is available at https://github.com/smlab-niser/clean-gs

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

GRAFT: Auditing Graph Neural Networks via Global Feature Attribution

Graph Neural Networks (GNNs) achieve strong performance on node classification tasks but remain difficult to interpret, particularly with respect to which input features drive their predictions. Existing global GNN explainers operate at the structural level identifying recurring subgraph motifs, but none explain model behaviour globally at the level of input node attributes. We propose GRAFT, a posthoc global explanation framework that identifies class-level feature importance profiles for GNNs. The method combines diversity-guided exemplar selection, Integrated Gradients-based attribution, and aggregation to construct a global view of feature influence for each class, which can be further expressed as concise natural language rules using a large language model with self-refinement. We evaluate GRAFT across multiple datasets, architectures, and experimental settings, demonstrating its effectiveness in capturing model-relevant features, supporting bias analysis, and enabling feature-efficient transfer learning. In addition, we introduce a structured human evaluation protocol to assess the interpretability of generated rules along dimensions such as accuracy and usefulness. Our results suggest that GRAFT provides a practical and interpretable approach for analysing feature-level behaviour in GNNs, bridging quantitative attribution with human-understandable explanations.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Graph Reconstruction from Differentially Private GNN Explanations

Regulatory frameworks such as GDPR increasingly require that ML predictions be accompanied by post-hoc explanations, even when raw data and trained models cannot be released. Differential privacy (DP) is the standard mitigation for the residual privacy risk of releasing these explanations. We show that DP is not sufficient: an adversary observing only DP-perturbed GNN explanations can reconstruct hidden graph structure with high accuracy. Our attack, PRIVX, exploits the fact that the Gaussian DP mechanism is a single DDPM forward step at known noise level σ(ε), recasting reconstruction as reverse diffusion conditioned on the corrupted signal, a principled Bayesian denoiser under known DP corruption. We formalise a stratified adversary model parameterised by (M, \hatε, \hatδ, S, ρ) that interpolates between oblivious and oracle attackers, and derive endpoint-matched two-sided bounds on reconstruction AUC. For practitioners, we provide regime-stratified guidance on explainer choice: on homophilic graphs, neighbourhood-aggregating explainers (GraphLIME, GNNExplainer) leak more structure than per-node gradient explainers under the same DP budget; on strongly heterophilic graphs the ordering reverses. We introduce PRIVF as an auxiliary diagnostic sharing the same diffusion backbone to decompose leakage into explainer-induced and intrinsic graph-distribution components. Experiments across seven benchmarks, three DP mechanisms, and three GNN backbones show PRIVX achieves AUC above 0.7 at ε = 5 on five of seven datasets, with the attack succeeding well within typically deployed privacy budgets.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

mHC-GNN: Manifold-Constrained Hyper-Connections for Graph Neural Networks

Graph Neural Networks (GNNs) suffer from over-smoothing in deep architectures and expressiveness bounded by the 1-Weisfeiler-Leman (1-WL) test. We adapt Manifold-Constrained Hyper-Connections (\mhc)~\citep{xie2025mhc}, recently proposed for Transformers, to graph neural networks. Our method, mHC-GNN, expands node representations across $n$ parallel streams and constrains stream-mixing matrices to the Birkhoff polytope via Sinkhorn-Knopp normalization. We prove that mHC-GNN exhibits exponentially slower over-smoothing (rate $(1-γ)^{L/n}$ vs.\ $(1-γ)^L$) and can distinguish graphs beyond 1-WL. Experiments on 10 datasets with 4 GNN architectures show consistent improvements. Depth experiments from 2 to 128 layers reveal that standard GNNs collapse to near-random performance beyond 16 layers, while mHC-GNN maintains over 74\% accuracy even at 128 layers, with improvements exceeding 50 percentage points at extreme depths. Ablations confirm that the manifold constraint is essential: removing it causes up to 82\% performance degradation. Code is available at \href{https://github.com/smlab-niser/mhc-gnn}{https://github.com/smlab-niser/mhc-gnn}

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Towards Metric-Faithful Neural Graph Matching

Graph Edit Distance (GED) is a fundamental, albeit NP-hard, metric for structural graph similarity. Recent neural graph matching architectures approximate GED by first encoding graphs with a Graph Neural Network (GNN) and then applying either a graph-level regression head or a matching-based alignment module. Despite substantial architectural progress, the role of encoder geometry in neural GED estimation remains poorly understood. In this paper, we develop a theoretical framework that connects encoder geometry to GED estimation quality for two broad classes of neural GED estimators: graph similarity predictors and alignment-based methods. On fixed graph collections, where the doubly-stochastic metric $d_{\mathrm{DS}}$ is comparable to GED, we show that graph-level bi-Lipschitz encoders yield controlled GED surrogates and improved ranking stability; for matching-based estimators, node-level bi-Lipschitz geometry propagates to encoder-induced alignment costs and the resulting optimized alignment objective. We instantiate this perspective using FSW-GNN, a bi-Lipschitz WL-equivalent encoder, as a drop-in replacement in representative neural GED architectures. Across representative baselines and benchmark datasets, the resulting geometry-aware variants significantly improve GED prediction and ranking metrics. A faithfulness case study of untrained encoders, together with ablations and transfer experiments, supports the view that these gains arise from improved representation geometry, positioning encoder geometry as a useful design principle for neural graph matching.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

Dict-NMT: Bilingual Dictionary based NMT for Extremely Low Resource Languages

Neural Machine Translation (NMT) models have been effective on large bilingual datasets. However, the existing methods and techniques show that the model's performance is highly dependent on the number of examples in training data. For many languages, having such an amount of corpora is a far-fetched dream. Taking inspiration from monolingual speakers exploring new languages using bilingual dictionaries, we investigate the applicability of bilingual dictionaries for languages with extremely low, or no bilingual corpus. In this paper, we explore methods using bilingual dictionaries with an NMT model to improve translations for extremely low resource languages. We extend this work to multilingual systems, exhibiting zero-shot properties. We present a detailed analysis of the effects of the quality of dictionaries, training dataset size, language family, etc., on the translation quality. Results on multiple low-resource test languages show a clear advantage of our bilingual dictionary-based method over the baselines.

0 citations0 reviewsNo code linkedOpen access
preprint2022arXiv

eBIM-GNN : Fast and Scalable energy analysis through BIMs and Graph Neural Networks

Building Information Modeling has been used to analyze as well as increase the energy efficiency of the buildings. It has shown significant promise in existing buildings by deconstruction and retrofitting. Current cities which were built without the knowledge of energy savings are now demanding better ways to become smart in energy utilization. However, the existing methods of generating BIMs work on building basis. Hence they are slow and expensive when we scale to a larger community or even entire towns or cities. In this paper, we propose a method to creation of prototype buildings that enable us to match and generate statistics very efficiently. Our method suggests better energy efficient prototypes for the existing buildings. The existing buildings are identified and located in the 3D point cloud. We perform experiments on synthetic dataset to demonstrate the working of our approach.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Indian Economy and Nighttime Lights

Forecasting economic growth of India has been traditionally an uncertain exercise. The indicators and factors affecting economic structures and the variables required to model that captures the situation correctly is point of concern. Although the forecast should be specific to the country we are looking at however countries do have interlinkages among them. As the time series can be more volatile and sometimes certain variables are unavailable it is harder to predict for the developing economies as compared to stable and developed nations. However it is very important to have accurate forecasts for economic growth for successful policy formations. One of the hypothesized indicators is the nighttime lights. Here we aim to look for a relationship between GDP and Nighttime lights. Specifically we look at the DMSP and VIIRS dataset. We are finding relationship between various measures of economy.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Learning Graph Representations

Social and information networks are gaining huge popularity recently due to their various applications. Knowledge representation through graphs in the form of nodes and edges should preserve as many characteristics of the original data as possible. Some of the interesting and useful applications on these graphs are graph classification, node classification, link prediction, etc. The Graph Neural Networks have evolved over the last few years. Graph Neural Networks (GNNs) are efficient ways to get insight into large and dynamic graph datasets capturing relationships among billions of entities also known as knowledge graphs. In this paper, we discuss the graph convolutional neural networks graph autoencoders and spatio-temporal graph neural networks. The representations of the graph in lower dimensions can be learned using these methods. The representations in lower dimensions can be used further for downstream machine learning tasks.

0 citations0 reviewsNo code linkedOpen access
preprint2021arXiv

Temporal Motifs in Smart Grid

A complex network can be characterized by patterns. Such frequently occurring significant patterns are called motifs and in a time dependent network, they are called temporal motifs. One of the temporal networks where temporal motifs are observed and play a major role; is the Smart Grid. The energy consumption pattern across the appliances, houses, communities and entire cities help energy utility companies and consumers plan their electricity generation and consumption. The temporal motifs for the smart grid constitutes of the consumers and producers and the edge or connection represents energy flow between two participants of the network, these connections last till the power is being consumed/generated. This paper formally defines the temporal motifs for smart grid network and proposes a way to create such temporal motifs in the network. We also discuss how the temporal motifs fit into the hierarchical structure of power distribution system of Smart Grid.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

ARA : Aggregated RAPPOR and Analysis for Centralized Differential Privacy

Differential privacy(DP) has now become a standard in case of sensitive statistical data analysis. The two main approaches in DP is local and central. Both the approaches have a clear gap in terms of data storing,amount of data to be analyzed, analysis, speed etc. Local wins on the speed. We have tested the state of the art standard RAPPOR which is a local approach and supported this gap. Our work completely focuses on that part too. Here, we propose a model which initially collects RAPPOR reports from multiple clients which are then pushed to a Tf-Idf estimation model. The Tf-Idf estimation model then estimates the reports on the basis of the occurrence of "on bit" in a particular position and its contribution to that position. Thus it generates a centralized differential privacy analysis from multiple clients. Our model successfully and efficiently analyzed the major truth value every time.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

BUDS: Balancing Utility and Differential Privacy by Shuffling

Balancing utility and differential privacy by shuffling or \textit{BUDS} is an approach towards crowd-sourced, statistical databases, with strong privacy and utility balance using differential privacy theory. Here, a novel algorithm is proposed using one-hot encoding and iterative shuffling with the loss estimation and risk minimization techniques, to balance both the utility and privacy. In this work, after collecting one-hot encoded data from different sources and clients, a step of novel attribute shuffling technique using iterative shuffling (based on the query asked by the analyst) and loss estimation with an updation function and risk minimization produces a utility and privacy balanced differential private report. During empirical test of balanced utility and privacy, BUDS produces $ε= 0.02$ which is a very promising result. Our algorithm maintains a privacy bound of $ε= ln [t/((n_1 - 1)^S)]$ and loss bound of $c' \bigg|e^{ln[t/((n_1 - 1)^S)]} - 1\bigg|$.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Comparative Sentiment Analysis of App Reviews

Google app market captures the school of thought of users via ratings and text reviews. The critique's viewpoint regarding an app is proportional to their satisfaction level. Consequently, this helps other users to gain insights before downloading or purchasing the apps. The potential information from the reviews can't be extracted manually, due to its exponential growth. Sentiment analysis, by machine learning algorithms employing NLP, is used to explicitly uncover and interpret the emotions. This study aims to perform the sentiment classification of the app reviews and identify the university students' behavior towards the app market. We applied machine learning algorithms using the TF-IDF text representation scheme and the performance was evaluated on the ensemble learning method. Our model was trained on Google reviews and tested on students' reviews. SVM recorded the maximum accuracy(93.37\%), F-score(0.88) on tri-gram + TF-IDF scheme. Bagging enhanced the performance of LR and NB with accuracy of 87.80\% and 85.5\% respectively.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Cyberattack on the Microgrids Through Price Modification

Recent massive failures in the power grid acted as a wake up call for all utilities and consumers. This leads to aggressive pursue a more intelligent grid which addresses the concerns of reliability, efficiency, security, quality and sustainability for the energy consumers and producers alike. One of the many features of the smart grid is a discrete energy system consisting of distributed energy sources capable of operating independently from the main grid known as the microgrid. The main focus of the microgrid is to ensure a reliable and affordable energy security. However, it also can be vulnerable to cyber attack and we study the effect of price modification of electricity attack on the microgrid, given that they are able to operate independently from the main grid. This attack consists of two stages, 1) Separate the microgrids from the main grid (islanding) and 2) Failing the nodes inside the microgrid. Empirical results on IEEE Bus data help us evaluate our approach under various settings of grid parameters.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Election in India: Polling in National Financial Switch

Indian voters from Kashmir to Kanyakumari select their representatives to form their parliament by going to polls. India's election is one of the largest democratic exercise in the world history. About 850 million eligible voters determine which political party or alliance will form the government and in turn, will serve as prime minister. Given the electoral rules of placing a polling place within 2 kilometers of every habitation, it comes as no surprise that is indeed a humongous task for the Election Commission of India (ECI). It sends around 11 million election workers through tough terrains to reach the last mile. This exercise also comes as ever growing expenditure for the ECI. This paper proposes the use of Automated Teller Machines (ATM) and Point Of Sale (POS) machines to be used to cover as much as urban, rural and semi-urban places possible given the wide network of National Financial Switch (NFS) and increase in connectivity through Digital India initiative. This would add to the use of the existing infrastructure to accommodate a free, fair and transparent election.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

FLaPS: Federated Learning and Privately Scaling

Federated learning (FL) is a distributed learning process where the model (weights and checkpoints) is transferred to the devices that posses data rather than the classical way of transferring and aggregating the data centrally. In this way, sensitive data does not leave the user devices. FL uses the FedAvg algorithm, which is trained in the iterative model averaging way, on the non-iid and unbalanced distributed data, without depending on the data quantity. Some issues with the FL are, 1) no scalability, as the model is iteratively trained over all the devices, which amplifies with device drops; 2) security and privacy trade-off of the learning process still not robust enough and 3) overall communication efficiency and the cost are higher. To mitigate these challenges we present Federated Learning and Privately Scaling (FLaPS) architecture, which improves scalability as well as the security and privacy of the system. The devices are grouped into clusters which further gives better privacy scaled turn around time to finish a round of training. Therefore, even if a device gets dropped in the middle of training, the whole process can be started again after a definite amount of time. The data and model both are communicated using differentially private reports with iterative shuffling which provides a better privacy-utility trade-off. We evaluated FLaPS on MNIST, CIFAR10, and TINY-IMAGENET-200 dataset using various CNN models. Experimental results prove FLaPS to be an improved, time and privacy scaled environment having better and comparable after-learning-parameters with respect to the central and FL models.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

India Growth Forecast for 2020-21

COVID-19 has put a severe dent on the global economy and Indian Economy. International Monetary Fund has projected 1.9 percent for India. However, we believe that due to extended lockdown, the output in the first quarter is almost wiped out. The situation may improve in the second quarter onwards. Nevertheless, due to demand and supply constraints, input constraints and disruption in the supply chain, except agriculture, no other sector would be able to achieve full capacity of production in 2020-21. The signals from power consumption, GST collection, contraction in the core sectors hint towards a slump in the total output production in 2020-21. We derive the quarterly GVA for 2020-21 by using certain assumptions on the capacity utilisation in different sectors and using the quarterly data of 2019-20. We provide quarterly estimates of Gross Value Addition for 2020-21 under two scenarios. We have also estimated the fourth quarter output for 2019-20 under certain assumptions. We estimate

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

LAC : LSTM AUTOENCODER with Community for Insider Threat Detection

The employees of any organization, institute, or industry, spend a significant amount of time on a computer network, where they develop their own routine of activities in the form of network transactions over a time period. Insider threat detection involves identifying deviations in the routines or anomalies which may cause harm to the organization in the form of data leaks and secrets sharing. If not automated, this process involves feature engineering for modeling human behavior which is a tedious and time-consuming task. Anomalies in human behavior are forwarded to a human analyst for final threat classification. We developed an unsupervised deep neural network model using LSTM AUTOENCODER which learns to mimic the behavior of individual employees from their day-wise time-stamped sequence of activities. It predicts the threat scenario via significant loss from anomalous routine. Employees in a community tend to align their routine with each other rather than the employees outside their communities, this motivates us to explore a variation of the AUTOENCODER, LSTM AUTOENCODER- trained on the interleaved sequences of activities in the Community (LAC). We evaluate the model on the CERT v6.2 dataset and perform analysis on the loss for normal and anomalous routine across 4000 employees. The aim of our paper is to detect the anomalous employees as well as to explore how the surrounding employees are affecting that employees' routine over time.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Learning With Differential Privacy

The leakage of data might have been an extreme effect on the personal level if it contains sensitive information. Common prevention methods like encryption-decryption, endpoint protection, intrusion detection system are prone to leakage. Differential privacy comes to the rescue with a proper promise of protection against leakage, as it uses a randomized response technique at the time of collection of the data which promises strong privacy with better utility. Differential privacy allows one to access the forest of data by describing their pattern of groups without disclosing any individual trees. The current adaption of differential privacy by leading tech companies and academia encourages authors to explore the topic in detail. The different aspects of differential privacy, it's application in privacy protection and leakage of information, a comparative discussion, on the current research approaches in this field, its utility in the real world as well as the trade-offs - will be discussed.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Threat from being Social: Vulnerability Analysis of Social Network Coupled Smart Grid

Social Networks (SNs) have been gradually applied by utility companies as an addition to smart grid and are proved to be helpful in smoothing load curves and reducing energy usage. However, SNs also bring in new threats to smart grid: misinformation in SNs may cause smart grid users to alter their demand, resulting in transmission line overloading and in turn leading to catastrophic impact to the grid. In this paper, we discuss the interdependency in the social network coupled smart grid and focus on its vulnerability. That is, how much can the smart grid be damaged when misinformation related to it diffuses in SNs? To analytically study the problem, we propose the Misinformation Attack Problem in Social-Smart Grid (MAPSS) that identifies the top critical nodes in the SN, such that the smart grid can be greatly damaged when misinformation propagates from those nodes. This problem is challenging as we have to incorporate the complexity of the two networks concurrently. Nevertheless, we propose a technique that can explicitly take into account information diffusion in SN, power flow balance and cascading failure in smart grid integratedly when evaluating node criticality, based on which we propose various strategies in selecting the most critical nodes. Also, we introduce controlled load shedding as a protection strategy to reduce the impact of cascading failure. The effectiveness of our algorithms are demonstrated by experiments on IEEE bus test cases as well as the Pegase data set.

0 citations0 reviewsNo code linkedOpen access
preprint2020arXiv

Usage Analysis of Mobile Devices

Mobile devices have evolved from just communication devices into an indispensable part of people's lives in form of smartphones, tablets and smart watches. Devices are now more personal than ever and carry more information about a person than any other. Extracting user behaviour is rather difficult and time-consuming as most of the work previously has been manual or requires feature extraction. In this paper, a novel approach of user behavior detection is proposed with Deep Learning Network (DNN). Initial approach was to use recurrent neural network (RNN) along with LSTM for completely unsupervised analysis of mobile devices. Next approach is to extract features by using Long Short Term Memory (LSTM) to understand the user behaviour, which are then fed into the Convolution Neural Network (CNN). This work mainly concentrates on detection of user behaviour and anomaly detection for usage analysis of mobile devices. Both the approaches are compared against some baseline methods. Experiments are conducted on the publicly available dataset to show that these methods can successfully capture the user behaviors.

0 citations0 reviewsNo code linkedOpen access