Upasna Singh | DIAT Pune (original) (raw)

Uploads

Papers by Upasna Singh

Lecture Notes in Electrical Engineering, 2020

Generative Modelling has been a very extensive area of research since it finds immense use cases ... more Generative Modelling has been a very extensive area of research since it finds immense use cases across multiple domains. Various models have been proposed in the recent past including Fully Visible Belief Nets, NADE, MADE, Pixel RNN Variational Auto Encoders, Markov Chain, and Generative Adversarial Networks. Amongst all the models, Generative Adversarial Networks have been consistently showing huge potential and developments in the area of Art, Music, SemiSupervised learning, Handling Missing data, Drug Discovery, and unsupervised learning. This emerging technology has reshaped the research landscape in the field of generative modeling. The research in the area of Generative Adversarial Networks (GANs) was introduced by Ian J. Goodfellow et al in 2014 [1]. However, since its inception, various models have been proposed over the years and are considered state-of-the-art models in generative modeling. In this survey, we provide a comprehensive review of the original GAN model and it...

Global Perspectives on Legal History, 2015

Advances in Intelligent Systems and Computing, 2018

Advances in Intelligent Systems and Computing

The emergence of novel devices with admissible computational and communication capabilities has r... more The emergence of novel devices with admissible computational and communication capabilities has resulted in fabrication of portable and customizable Internet of Things (IoT) products like Raspberry Pi (RPi). The rapid proliferation of such devices has created new opportunities for offensive users and offers considerable challenges to digital investigators. It is necessary for investigators to diligently understand the implicit data formats and the types of evidence present in such devices. In this chapter, we present trade-off triangle which highlights the importance of digital forensics process towards the scenario of IoT enabled services. This chapter also proposes a common methodology for investigating forensic artifacts on IoT prototyping hardware platform. Based on the proposed methodology, a proof-of-concept tool called as RIFT has been developed as an outcome of research that aims the acquisition and preservation of forensically relevant static as well as volatile artifacts from RPi-IoT platform. Several experiments were carried out on the considered platform to reveal the vital evidence that can noticeably assist in forensic investigation. Finally, the preserved evidences are evaluated and presented to illustrate their usefulness and significances in digital forensic.

International Journal of Computer and Communication Technology

Since the improvement in Anti Radar Material technology and stealth technology grows, there are i... more Since the improvement in Anti Radar Material technology and stealth technology grows, there are immense counter measures that have opened to deny such technologies for classification to the adversary. At the same time it is observed that radar is continuously tracking the air target. This track data represents the kinematics which can be efficiently manipulated for effective classification without being deceived. The present study uses decision tree based classifier, specifically Classification and Regression Tree (CRT) algorithm over certain significant feature vectors. It classifies the data set of an air target into a target class where feature vectors are derived from the Radar Track Data using Matlab code. The work presented here aims to assess the performance of CRT. Although the methods and results presented here are for Air Target Classification, they may give insight for other applications.