Please use this identifier to cite or link to this item: http://hdl.handle.net/123456789/1549
Full metadata record
DC FieldValueLanguage
dc.contributor.authorGopal, Bhavish Raj.-
dc.contributor.authorJena, Satyajit-
dc.date.accessioned2021-12-08T17:40:48Z-
dc.date.available2021-12-08T17:40:48Z-
dc.date.issued2021-07-28-
dc.identifier.urihttp://hdl.handle.net/123456789/1549-
dc.description.abstractIn the last decade, there has been an increase in technologies involving applications of Ma- chine Learning. For instance, Hospitals use Machine Learning tools to predict a disease; Navigation systems predict traffic flow using machine Learning. In the heart of all this tech- nology is sensitive user data, which has led to several privacy concerns. The development of privacy-enhancing technologies enabled systems to collect and perform computations on data while preserving privacy. We can use several cryptographic tools to develop privacy-enhancing technologies. Multi- party computation(MPC) is one such cryptographic tool where non-colluding parties per- form joint computation over data. Privacy is preserved by no party having any information about the data being computed on. In our work, we focus on implementing Multi-Party Computation(MPC) techniques in Machine Learning setting. More specifically, we fo- cus on improving SecureNN, a three-party secure computation framework for Neural Net- works(NN) training, and inference. The SecureNN framework is state-of-the-art; however, it is mainly limited to Convolutional Neural Networks(CNN). In our work, we extend the SecureNN framework to other neural networks such as RNNs, GRU, and LSTMs. We also work on making SecureNN user- friendly by integrating it with TensorFlow. For this, we make significant improvements to the CrypTFlow, a framework for secure inference in TensorFlow. We implement secure training in CrypTFlow by implementing Secure Training functionalities from SecureNN. We also explore ML algorithms that are computationally less expensive and enable parallel computations to reduce the overheads of SecureNN.en_US
dc.language.isoen_USen_US
dc.publisherIISERMen_US
dc.subjectSecureen_US
dc.subjectMachineen_US
dc.subjectLearningen_US
dc.titleSecure machine learningen_US
dc.typeThesisen_US
Appears in Collections:MS-16

Files in This Item:
File Description SizeFormat 
MS16049.docx12.21 kBMicrosoft Word XMLView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.