Development of privacy preserving machine learning techniques using secure multi party computation

dc.contributor.guideGeorge, Jossy P
dc.coverage.spatial
dc.creator.researcherTiwari, Kapil
dc.date.accessioned2024-02-27T12:09:02Z
dc.date.available2024-02-27T12:09:02Z
dc.date.awarded2024
dc.date.completed2023
dc.date.registered2020
dc.description.abstractMachine learning (ML) has brought about a paradigm shift in insight generation across various domains, including healthcare, finance, and pharma, by leveraging historical data. However, the effectiveness of ML solutions hinges on the seamless collaboration between data owners, model owners, and ML clients while ensuring that privacy concerns are meticulously addressed. Unfortunately, existing privacy-preserving solutions have not been able to offer efficient and confidential ML training and inference. This has led to an increased focus on Privacy-Preserving Machine Learning (PPML), which has become a flourishing area of research aimed at safeguarding the privacy of machine learning stakeholders. In this regard, the present research introduces novel techniques for private ML inference and training of models using Secure Multi-Party Computation (SMPC) and Differential Privacy (DP) methods on horizontally and vertically partitioned datasets. The proposed techniques are implemented using Python with open-source libraries such as SyMPC and PyDP to ensure confidential inference and model protection. The findings across various parameters illustrate the effectiveness of the suggested techniques in addressing the privacy concerns of model owners and inference clients, with no significant impact on accuracy and a linear influence on performance as the privacy parameters, such as secure nodes count within the SMPC cluster. are increased. Furthermore, the privacy gain is substantiated by information privacy measures such as Mutual Information and KL-Divergence across different privacy budgets, which demonstrate empirically that privacy can be preserved with high ML accuracy and minimal performance cost.
dc.description.note
dc.format.accompanyingmaterialNone
dc.format.dimensionsA4
dc.format.extentv, 102p.;
dc.identifier.urihttp://hdl.handle.net/10603/548041
dc.languageEnglish
dc.publisher.institutionDepartment of Computer Science
dc.publisher.placeBangalore
dc.publisher.universityCHRIST University
dc.relation108
dc.rightsuniversity
dc.source.universityUniversity
dc.subject.keywordComputer Science
dc.subject.keywordComputer Science Artificial Intelligence
dc.subject.keywordConfidential Inference and Model Protection.
dc.subject.keywordEngineering and Technology
dc.subject.keywordMachine Learning (ML),
dc.subject.keywordPrivacy,
dc.subject.keywordPrivacy-Preserving Machine Learning (PPML),
dc.subject.keywordSecure Multi-Party Computation (SMPC),
dc.titleDevelopment of privacy preserving machine learning techniques using secure multi party computation
dc.title.alternative
dc.type.degreePh.D.

Files

Original bundle

Now showing 1 - 5 of 13
Loading...
Thumbnail Image
Name:
01_title.pdf
Size:
187.59 KB
Format:
Adobe Portable Document Format
Description:
Attached File
Loading...
Thumbnail Image
Name:
02_prelim pages.pdf
Size:
944.52 KB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
03_abstract.pdf
Size:
80.23 KB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
04_table_of_contents.pdf
Size:
116.47 KB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
05_chapter1.pdf
Size:
150.8 KB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.79 KB
Format:
Plain Text
Description: