<?xml version="1.0" encoding="UTF-8"?><?xml-stylesheet type="text/xsl" href="static/style.xsl"?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-11-22T22:37:41Z</responseDate><request verb="GetRecord" identifier="oai:uwspace.uwaterloo.ca:10012/23295" metadataPrefix="dim">https://dspacemainprd01.lib.uwaterloo.ca/server/oai/request</request><GetRecord><record><header><identifier>oai:uwspace.uwaterloo.ca:10012/23295</identifier><datestamp>2026-05-13T15:25:27Z</datestamp><setSpec>com_10012_9860</setSpec><setSpec>com_10012_1</setSpec><setSpec>col_10012_9864</setSpec><setSpec>col_10012_6</setSpec></header><metadata><dim:dim xmlns:dim="http://www.dspace.org/xmlns/dspace/dim" xmlns:doc="http://www.lyncode.com/xoai" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.dspace.org/xmlns/dspace/dim http://www.dspace.org/schema/dim.xsd">
   <dim:field mdschema="dc" element="contributor" qualifier="author">Padalko, Kateryna</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="accessioned">2026-05-13T15:25:27Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="available">2026-05-13T15:25:27Z</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="issued">2026-05-13</dim:field>
   <dim:field mdschema="dc" element="date" qualifier="submitted">2026-05-08</dim:field>
   <dim:field mdschema="dc" element="identifier" qualifier="uri">https://hdl.handle.net/10012/23295</dim:field>
   <dim:field mdschema="dc" element="description" qualifier="abstract">Training generative models under differential privacy (DP) requires injecting calibrated noise into gradient updates, creating an inherent trade-off between privacy protection and data quality. In standard DP-CTGAN, a single discriminator processes all features under a shared privacy budget, so noise injected to protect sensitive demographic attributes equally degrades the learning signal for non-sensitive features, an architectural limitation, not a mathematical one. 
We propose the Dual-Path DP-CTGAN, a discriminator architecture that partitions features into sensitive and non-sensitive paths, each governed by its own DP-SGD mechanism and Rényi DP accountant. Gradient isolation confines privacy noise to its respective path, preserving the learning signal for non-sensitive features without relaxing the formal (ε, δ)-DP guarantee. By the post-processing theorem, the generator inherits the privacy guarantees of both paths without additional composition. We embed this architecture in a Bayesian multi-objective hyperparameter optimisation pipeline that jointly evaluates utility, distributional fidelity, and empirical privacy risk, using Pareto-dominance selection to surface non-dominated configurations. 
Experiments on the Adult Census Income benchmark demonstrate that Dual-Path at ε = 1 achieves distributional fidelity below the non-private baseline and reduces the downstream utility gap by 79% relative to single-path DP-CTGAN at the same budget, exceeding single-path performance at ε = 5 while maintaining comparable empirical privacy risk. Per-feature analysis confirms that the fidelity gain concentrates in the feature group freed from cross-path noise contamination, providing direct evidence for the gradient isolation mechanism. These results suggest that discriminator architecture, rather than the noise mechanism itself, is the primary bottleneck limiting utility in standard DP-GAN designs.</dim:field>
   <dim:field mdschema="dc" element="language" qualifier="iso">en</dim:field>
   <dim:field mdschema="dc" element="publisher" lang="en">University of Waterloo</dim:field>
   <dim:field mdschema="dc" element="subject">differential privacy</dim:field>
   <dim:field mdschema="dc" element="subject">synthetic data generation</dim:field>
   <dim:field mdschema="dc" element="subject">privacy–utility trade-off</dim:field>
   <dim:field mdschema="dc" element="subject">tabular data synthesis</dim:field>
   <dim:field mdschema="dc" element="subject">health data privacy</dim:field>
   <dim:field mdschema="dc" element="subject">Dual-Path DP-CTGAN</dim:field>
   <dim:field mdschema="dc" element="subject">conditional tabular GAN</dim:field>
   <dim:field mdschema="dc" element="subject">Pareto optimization</dim:field>
   <dim:field mdschema="dc" element="subject">privacy risk evaluation</dim:field>
   <dim:field mdschema="dc" element="title">Adaptive Differential Privacy Budgeting Strategy for Optimizing Synthetic Data Generation and Privacy–Utility Trade-offs</dim:field>
   <dim:field mdschema="dc" element="type">Master Thesis</dim:field>
   <dim:field mdschema="dc" element="pending">false</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="department">School of Public Health Sciences</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="discipline">Public Health Sciences</dim:field>
   <dim:field mdschema="uws-etd" element="degree" qualifier="grantor" lang="en">University of Waterloo</dim:field>
   <dim:field mdschema="uws-etd" element="degree">Master of Science</dim:field>
   <dim:field mdschema="uws-etd" element="embargo" qualifier="terms">0</dim:field>
   <dim:field mdschema="uws" element="contributor" qualifier="advisor">Chen, Helen</dim:field>
   <dim:field mdschema="uws" element="contributor" qualifier="affiliation1">Faculty of Health</dim:field>
   <dim:field mdschema="uws" element="published" qualifier="city" lang="en">Waterloo</dim:field>
   <dim:field mdschema="uws" element="published" qualifier="country" lang="en">Canada</dim:field>
   <dim:field mdschema="uws" element="published" qualifier="province" lang="en">Ontario</dim:field>
   <dim:field mdschema="uws" element="typeOfResource" lang="en">Text</dim:field>
   <dim:field mdschema="uws" element="peerReviewStatus" lang="en">Unreviewed</dim:field>
   <dim:field mdschema="uws" element="scholarLevel" lang="en">Graduate</dim:field>
   <dim:field mdschema="others" element="access-status">open.access</dim:field>
</dim:dim>
</metadata></record></GetRecord></OAI-PMH>