University of British Columbia
A kernel-based approach to differentially private image generation
Abstract
dc:descriptionThe gold standard privacy notion, differential privacy (DP), has gained widespread adoption in academic research, industry products, and government databases due to its mathematically provable privacy guarantee. However, the composability property of DP leads to privacy degradation with multiple accesses to the same data. Differentially private data generation has emerged as a solution, creating synthetic datasets resembling private data while allowing repeated access without additional privacy loss. Existing methods often assume specific use cases for synthetic data, limiting flexibility. This thesis addresses the challenge of producing flexible synthetic data by leveraging deep generative modeling and addressing privacy loss in other methods such as generative adversarial networks (GAN). we propose utilizing public data to learn perceptual features (PFs) for comparing real and synthetic data distributions, employing a non-adversarial generator training scheme based on Maximum Mean Discrepancy (MMD) to mitigate privacy loss. Experimental results reveal the efficacy of our method. it successfully generates samples for CIFAR-10, CelebA, MNIST, and FashionMNIST. Theoretical analysis of our privacy-preserving loss function clarifies the privacy-accuracy trade-offs.
Degree
thesis:*- Name thesis:degree_name
- Master of Science - MSc
- Level thesis:degree_level
- master's
- Discipline thesis:degree_discipline
- Computer Science
- Grantor dc:publisher
- University of British Columbia
- Year dc:date
- 2023
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Jalali Asadabadi, Milad
- Contributors dc:contributor
-
- Sutherland, Danica J.
Rights
dc:rights- Statement dc:rights
-
- Attribution-ShareAlike 4.0 International
- Language dc:language
- eng
Identifiers
dc:identifier.*- Handle dc:identifier
- http://hdl.handle.net/2429/86181