arXiv subjects

Neeraj Kumar

Publications and source records attributed to Neeraj Kumar.

At least 73 records · Page 4Linked to original sources

arXiv2021

Security in Next Generation Mobile Payment Systems: A Comprehensive Survey

Cash payment is still king in several markets, accounting for more than 90\ of the payments in almost all the developing countries. The usage of mobile phones is pretty ordinary in this present era. Mobile phones have become an inseparable friend for many users, serving much more than just communication tools. Every subsequent person is heavily relying on them due to multifaceted usage and affordability. Every person wants to manage his/her daily transactions and related issues by using his/her mobile phone. With the rise and advancements of mobile-specific security, threats are evolving as well. In this paper, we provide a survey of various security models for mobile phones. We explore multiple proposed models of the mobile payment system (MPS), their technologies and comparisons, payment methods, different security mechanisms involved in MPS, and provide analysis of the encryption technologies, authentication methods, and firewall in MPS. We also present current challenges and future directions of mobile phone security.

cs.CR↗

arXiv2021

Evening the Score: Targeting SARS-CoV-2 Protease Inhibition in Graph Generative Models for Therapeutic Candidates

We examine a pair of graph generative models for the therapeutic design of novel drug candidates targeting SARS-CoV-2 viral proteins. Due to a sense of urgency, we chose well-validated models with unique strengths: an autoencoder that generates molecules with similar structures to a dataset of drugs with anti-SARS activity and a reinforcement learning algorithm that generates highly novel molecules. During generation, we explore optimization toward several design targets to balance druglikeness, synthetic accessability, and anti-SARS activity based on \icfifty. This generative framework\footnote{https://github.com/exalearn/covid-drug-design} will accelerate drug discovery in future pandemics through the high-throughput generation of targeted therapeutic candidates.

q-bio.BM↗

arXiv2021

FedDPGAN: Federated Differentially Private Generative Adversarial Networks Framework for the Detection of COVID-19 Pneumonia

Existing deep learning technologies generally learn the features of chest X-ray data generated by Generative Adversarial Networks (GAN) to diagnose COVID-19 pneumonia. However, the above methods have a critical challenge: data privacy. GAN will leak the semantic information of the training data which can be used to reconstruct the training samples by attackers, thereby this method will leak the privacy of the patient. Furthermore, for this reason that is the limitation of the training data sample, different hospitals jointly train the model through data sharing, which will also cause the privacy leakage. To solve this problem, we adopt the Federated Learning (FL) frame-work which is a new technique being used to protect the data privacy. Under the FL framework and Differentially Private thinking, we propose a FederatedDifferentially Private Generative Adversarial Network (FedDPGAN) to detectCOVID-19 pneumonia for sustainable smart cities. Specifically, we use DP-GAN to privately generate diverse patient data in which differential privacy technology is introduced to make sure the privacy protection of the semantic information of training dataset. Furthermore, we leverage FL to allow hospitals to collaboratively train COVID-19 models without sharing the original data. Under Independent and Identically Distributed (IID) and non-IID settings, The evaluation of the proposed model is on three types of chest X-ray (CXR) images dataset (COVID-19, normal, and normal pneumonia). A large number of the truthful reports make the verification of our model can effectively diagnose COVID-19 without compromising privacy.

eess.IV↗

arXiv2021

Phase transitions in D-dimensional Gauss-Bonnet-Born-Infeld AdS black holes

In this paper, we have investigated the phase transition in black holes when Gauss-Bonnet corrections to the spacetime curvature and Born-Infeld extension in stress-energy tensor of electromagnetic field are considered in a negative cosmological constant background. It is evident that the black hole undergoes a phase transition as the specific heat capacity at constant potential shows discontinuities. Further, the computation of the free energy of the black hole, the Ehrenfest scheme and the Ruppeiner state space geometry analysis are carried out to establish the second order nature of this phase transition. The effect of non-linearity arising from Born-Infeld electrodynamics is also evident from our analysis. Our investigations are done in general D-spacetime dimensions with D > 4, and specific computations have been carried out in D = 5, 6, 7 spacetime dimensions.

gr-qc↗

arXiv2021

One Shot Audio to Animated Video Generation

We consider the challenging problem of audio to animated video generation. We propose a novel method OneShotAu2AV to generate an animated video of arbitrary length using an audio clip and a single unseen image of a person as an input. The proposed method consists of two stages. In the first stage, OneShotAu2AV generates the talking-head video in the human domain given an audio and a person's image. In the second stage, the talking-head video from the human domain is converted to the animated domain. The model architecture of the first stage consists of spatially adaptive normalization based multi-level generator and multiple multilevel discriminators along with multiple adversarial and non-adversarial losses. The second stage leverages attention based normalization driven GAN architecture along with temporal predictor based recycle loss and blink loss coupled with lipsync loss, for unsupervised generation of animated video. In our approach, the input audio clip is not restricted to any specific language, which gives the method multilingual applicability. OneShotAu2AV can generate animated videos that have: (a) lip movements that are in sync with the audio, (b) natural facial expressions such as blinks and eyebrow movements, (c) head movements. Experimental evaluation demonstrates superior performance of OneShotAu2AV as compared to U-GAT-IT and RecycleGan on multiple quantitative metrics including KID(Kernel Inception Distance), Word error rate, blinks/sec

cs.CV↗

arXiv2021

Artificial Intelligence based Autonomous Molecular Design for Medical Therapeutic: A Perspective

Domain-aware machine learning (ML) models have been increasingly adopted for accelerating small molecule therapeutic design in the recent years. These models have been enabled by significant advancement in state-of-the-art artificial intelligence (AI) and computing infrastructures. Several ML architectures are pre-dominantly and independently used either for predicting the properties of small molecules, or for generating lead therapeutic candidates. Synergetically using these individual components along with robust representation and data generation techniques autonomously in closed loops holds enormous promise for accelerated drug design which is a time consuming and expensive task otherwise. In this perspective, we present the most recent breakthrough achieved by each of the components, and how such autonomous AI and ML workflow can be realized to radically accelerate the hit identification and lead optimization. Taken together, this could significantly shorten the timeline for end-to-end antiviral discovery and optimization times to weeks upon the arrival of a novel zoonotic transmission event. Our perspective serves as a guide for researchers to practice autonomous molecular design in therapeutic discovery.

cs.LG↗

arXiv2021

Benchmarking Deep Graph Generative Models for Optimizing New Drug Molecules for COVID-19

Design of new drug compounds with target properties is a key area of research in generative modeling. We present a small drug molecule design pipeline based on graph-generative models and a comparison study of two state-of-the-art graph generative models for designing COVID-19 targeted drug candidates: 1) a variational autoencoder-based approach (VAE) that uses prior knowledge of molecules that have been shown to be effective for earlier coronavirus treatments and 2) a deep Q-learning method (DQN) that generates optimized molecules without any proximity constraints. We evaluate the novelty of the automated molecule generation approaches by validating the candidate molecules with drug-protein binding affinity models. The VAE method produced two novel molecules with similar structures to the antiretroviral protease inhibitor Indinavir that show potential binding affinity for the SARS-CoV-2 protein target 3-chymotrypsin-like protease (3CL-protease).

cs.LG↗

arXiv2021

The Maximum Exposure Problem

Given a set of points $P$ and axis-aligned rectangles $\mathcal{R}$ in the plane, a point $p \in P$ is called \emph{exposed} if it lies outside all rectangles in $\mathcal{R}$. In the \emph{max-exposure problem}, given an integer parameter $k$, we want to delete $k$ rectangles from $\mathcal{R}$ so as to maximize the number of exposed points. We show that the problem is NP-hard and assuming plausible complexity conjectures is also hard to approximate even when rectangles in $\mathcal{R}$ are translates of two fixed rectangles. However, if $\mathcal{R}$ only consists of translates of a single rectangle, we present a polynomial-time approximation scheme. For range space defined by general rectangles, we present a simple $O(k)$ bicriteria approximation algorithm; that is by deleting $O(k^2)$ rectangles, we can expose at least $Ω(1/k)$ of the optimal number of points.

cs.CG↗

arXiv2020

Few Shot Adaptive Normalization Driven Multi-Speaker Speech Synthesis

The style of the speech varies from person to person and every person exhibits his or her own style of speaking that is determined by the language, geography, culture and other factors. Style is best captured by prosody of a signal. High quality multi-speaker speech synthesis while considering prosody and in a few shot manner is an area of active research with many real-world applications. While multiple efforts have been made in this direction, it remains an interesting and challenging problem. In this paper, we present a novel few shot multi-speaker speech synthesis approach (FSM-SS) that leverages adaptive normalization architecture with a non-autoregressive multi-head attention model. Given an input text and a reference speech sample of an unseen person, FSM-SS can generate speech in that person's style in a few shot manner. Additionally, we demonstrate how the affine parameters of normalization help in capturing the prosodic features such as energy and fundamental frequency in a disentangled fashion and can be used to generate morphed speech output. We demonstrate the efficacy of our proposed architecture on multi-speaker VCTK and LibriTTS datasets, using multiple quantitative metrics that measure generated speech distortion and MoS, along with speaker embedding analysis of the generated speech vs the actual speech samples.

eess.AS↗

arXiv2020

Multi Modal Adaptive Normalization for Audio to Video Generation

Speech-driven facial video generation has been a complex problem due to its multi-modal aspects namely audio and video domain. The audio comprises lots of underlying features such as expression, pitch, loudness, prosody(speaking style) and facial video has lots of variability in terms of head movement, eye blinks, lip synchronization and movements of various facial action units along with temporal smoothness. Synthesizing highly expressive facial videos from the audio input and static image is still a challenging task for generative adversarial networks. In this paper, we propose a multi-modal adaptive normalization(MAN) based architecture to synthesize a talking person video of arbitrary length using as input: an audio signal and a single image of a person. The architecture uses the multi-modal adaptive normalization, keypoint heatmap predictor, optical flow predictor and class activation map[58] based layers to learn movements of expressive facial components and hence generates a highly expressive talking-head video of the given person. The multi-modal adaptive normalization uses the various features of audio and video such as Mel spectrogram, pitch, energy from audio signals and predicted keypoint heatmap/optical flow and a single image to learn the respective affine parameters to generate highly expressive video. Experimental evaluation demonstrates superior performance of the proposed method as compared to Realistic Speech-Driven Facial Animation with GANs(RSDGAN) [53], Speech2Vid [10], and other approaches, on multiple quantitative metrics including: SSIM (structural similarity index), PSNR (peak signal to noise ratio), CPBD (image sharpness), WER(word error rate), blinks/sec and LMD(landmark distance). Further, qualitative evaluation and Online Turing tests demonstrate the efficacy of our approach.

cs.CV↗

arXiv2020

Robust One Shot Audio to Video Generation

Audio to Video generation is an interesting problem that has numerous applications across industry verticals including film making, multi-media, marketing, education and others. High-quality video generation with expressive facial movements is a challenging problem that involves complex learning steps for generative adversarial networks. Further, enabling one-shot learning for an unseen single image increases the complexity of the problem while simultaneously making it more applicable to practical scenarios. In the paper, we propose a novel approach OneShotA2V to synthesize a talking person video of arbitrary length using as input: an audio signal and a single unseen image of a person. OneShotA2V leverages curriculum learning to learn movements of expressive facial components and hence generates a high-quality talking-head video of the given person. Further, it feeds the features generated from the audio input directly into a generative adversarial network and it adapts to any given unseen selfie by applying fewshot learning with only a few output updation epochs. OneShotA2V leverages spatially adaptive normalization based multi-level generator and multiple multi-level discriminators based architecture. The input audio clip is not restricted to any specific language, which gives the method multilingual applicability. Experimental evaluation demonstrates superior performance of OneShotA2V as compared to Realistic Speech-Driven Facial Animation with GANs(RSDGAN) [43], Speech2Vid [8], and other approaches, on multiple quantitative metrics including: SSIM (structural similarity index), PSNR (peak signal to noise ratio) and CPBD (image sharpness). Further, qualitative evaluation and Online Turing tests demonstrate the efficacy of our approach.

cs.CV↗

arXiv2020

Mitigating the Impact of Adversarial Attacks in Very Deep Networks

Deep Neural Network (DNN) models have vulnerabilities related to security concerns, with attackers usually employing complex hacking techniques to expose their structures. Data poisoning-enabled perturbation attacks are complex adversarial ones that inject false data into models. They negatively impact the learning process, with no benefit to deeper networks, as they degrade a model's accuracy and convergence rates. In this paper, we propose an attack-agnostic-based defense method for mitigating their influence. In it, a Defensive Feature Layer (DFL) is integrated with a well-known DNN architecture which assists in neutralizing the effects of illegitimate perturbation samples in the feature space. To boost the robustness and trustworthiness of this method for correctly classifying attacked input samples, we regularize the hidden space of a trained model with a discriminative loss function called Polarized Contrastive Loss (PCL). It improves discrimination among samples in different classes and maintains the resemblance of those in the same class. Also, we integrate a DFL and PCL in a compact model for defending against data poisoning attacks. This method is trained and tested using the CIFAR-10 and MNIST datasets with data poisoning-enabled perturbation attacks, with the experimental results revealing its excellent performance compared with those of recent peer techniques.

cs.CV↗

arXiv2020

A Constant Factor Approximation for Navigating Through Connected Obstacles in the Plane

Given two points s and t in the plane and a set of obstacles defined by closed curves, what is the minimum number of obstacles touched by a path connecting s and t? This is a fundamental and well-studied problem arising naturally in computational geometry, graph theory (under the names Min-Color Path and Minimum Label Path), wireless sensor networks (Barrier Resilience) and motion planning (Minimum Constraint Removal). It remains NP-hard even for very simple-shaped obstacles such as unit-length line segments. In this paper we give the first constant factor approximation algorithm for this problem, resolving an open problem of [Chan and Kirkpatrick, TCS, 2014] and [Bandyapadhyay et al., CGTA, 2020]. We also obtain a constant factor approximation for the Minimum Color Prize Collecting Steiner Forest where the goal is to connect multiple request pairs (s1, t1), . . . ,(sk, tk) while minimizing the number of obstacles touched by any (si, ti) path plus a fixed cost of wi for each pair (si, ti) left disconnected. This generalizes the classic Steiner Forest and Prize-Collecting Steiner Forest problems on planar graphs, for which intricate PTASes are known. In contrast, no PTAS is possible for Min-Color Path even on planar graphs since the problem is known to be APXhard [Eiben and Kanj, TALG, 2020]. Additionally, we show that generalizations of the problem to disconnected obstacles

cs.CG↗

arXiv2020

Efficient Power-Splitting and Resource Allocation for Cellular V2X Communications

The research efforts on cellular vehicle-to-everything (V2X) communications are gaining momentum with each passing year. It is considered as a paradigm-altering approach to connect a large number of vehicles with minimal cost of deployment and maintenance. This article aims to further push the state-of-the-art of cellular V2X communications by providing an optimization framework for wireless charging, power allocation, and resource block assignment. Specifically, we design a network model where roadside objects use wireless power from RF signals of electric vehicles for charging and information processing. Moreover, due to the resource-constraint nature of cellular V2X, the power allocation and resource block assignment are performed to efficiently use the resources. The proposed optimization framework shows an improvement in terms of the overall energy efficiency of the network when compared with the baseline technique. The performance gains of the proposed solution clearly demonstrate its feasibility and utility for cellular V2X communications.

eess.SP↗

arXiv2020

Systematically designing better instance counting models on cell images with Neural Arithmetic Logic Units

The big problem for neural network models which are trained to count instances is that whenever test range goes high training range generalization error increases i.e. they are not good generalizers outside training range. Consider the case of automating cell counting process where more dense images with higher cell counts are commonly encountered as compared to images used in training data. By making better predictions for higher ranges of cell count we are aiming to create better generalization systems for cell counting. With architecture proposal of neural arithmetic logic units (NALU) for arithmetic operations, task of counting has become feasible for higher numeric ranges which were not included in training data with better accuracy. As a part of our study we used these units and different other activation functions for learning cell counting task with two different architectures namely Fully Convolutional Regression Network and U-Net. These numerically biased units are added in the form of residual concatenated layers to original architectures and a comparative experimental study is done with these newly proposed changes. This comparative study is described in terms of optimizing regression loss problem from these models trained with extensive data augmentation techniques. We were able to achieve better results in our experiments of cell counting tasks with introduction of these numerically biased units to already existing architectures in the form of residual layer concatenation connections. Our results confirm that above stated numerically biased units does help models to learn numeric quantities for better generalization results.

cs.LG↗

arXiv2020

Anomalous planar Hall effect in a kagome ferromagnet

The macroscopic signature for Weyl nodes so far has been the negative longitudinal magnetoresistance arising from the chiral anomaly. However, negative longitudinal magnetoresistance is not unique to chiral anomaly and can arise due to completely different mechanisms such as current jetting or in ferromagnetic systems due to the suppression of scattering with magnons. Therefore, a macroscopic effect that can be uniquely attributed to the presence of Weyl nodes is desirable. Here we show that the planar Hall effect could be a hallmark for Weyl nodes. We investigated the anisotropic magnetoresistance and planar Hall effect in Fe$_3$Sn$_2$, which has a kagome lattice and has been predicted to be a type II Weyl metal. We discover that the planar Hall effect contains a field antisymmetric contribution in addition to the ordinary field symmetric contribution. The field antisymmetric planar Hall effect has a 3-fold rotational symmetry, distinctively different from the symmetric planar Hall effect, but consistent with the 3-fold rotational degeneracy of the magnetization in Fe$_3$Sn$_2$. The temperature and field dependence of the antisymmetric planar Hall effect rules out an interpretation based on contribution from the anomalous Hall effect and is different from the symmetric planar Hall effect, pointing to a different origin. We attribute the antisymmetric planar Hall effect to the topological nature of Fe$_3$Sn$_2$ due to the presence of Weyl II nodes. Our finding offers a promising route for macroscopically probing Weyl systems.

cond-mat.mes-hall↗

arXiv2020

Thermopower and Unconventional Nernst in the Predicted Type-II Weyl Semi-metal WTe$_2$

WTe$_2$ is one of a series of recently discovered high mobility semimetals, some of whose properties are characteristic of topological Dirac or Weyl metals. One of its most interesting properties is the unsaturated giant magnetoresistance that it exhibits at low temperatures. An important question is the degree to which this property can be ascribed to a conventional semi-metallic model in which a highly compensated, high mobility metal exhibits large magnetoresistance. Here we show that the longitudinal thermopower (Seebeck effect) of semi-metallic WTe$_2$ exfoliated flakes exhibits periodic sign changes about zero with increasing magnetic field that indicates distinct electron and hole Landau levels and nearly fully compensated electron and hole carrier densities. However, inconsistent with a conventional semi-metallic picture, we find a rapid enhancement of the Nernst effect at low temperatures that is nonlinear in magnetic field, which is consistent with Weyl points in proximity to the Fermi energy. Hence, we demonstrate the role played by the Weyl character of WTe$_2$ in its transport properties.

cond-mat.mes-hall↗

arXiv2020

Uncertainty Estimation in Cancer Survival Prediction

Survival models are used in various fields, such as the development of cancer treatment protocols. Although many statistical and machine learning models have been proposed to achieve accurate survival predictions, little attention has been paid to obtain well-calibrated uncertainty estimates associated with each prediction. The currently popular models are opaque and untrustworthy in that they often express high confidence even on those test cases that are not similar to the training samples, and even when their predictions are wrong. We propose a Bayesian framework for survival models that not only gives more accurate survival predictions but also quantifies the survival uncertainty better. Our approach is a novel combination of variational inference for uncertainty estimation, neural multi-task logistic regression for estimating nonlinear and time-varying risk models, and an additional sparsity-inducing prior to work with high dimensional data.

cs.LG↗