Document type
Bachelor thesisPublication date
Publication license
Please use this identifier to cite or link to this item: https://hdl.handle.net/2445/223909
Differentially Private Machine Learning: Implementation and Analysis of Gradient and Dataset Perturbation Techniques
Journal Title
Authors
Director/Tutor
Journal ISSN
Volume Title
Related resource
Abstract
The increasing use of machine learning poses significant privacy risks, especially when sensitive data is used, and conventional anonymization methods have proven insufficient. Differential privacy is a rigorous framework for data privacy providing strong mathematical guarantees. The possibility of applying this framework to machine learning solves the privacy problem. We will present the fundamental basis of these concepts to empirically investigate, implement, and analyse two techniques for integrating differential privacy into machine learning pipelines. The first technique, dataset perturbation, involves adding calibrated Gaussian noise directly to the training data and then using any standard machine learning pipeline. The second, gradient perturbation, centers on differentially private stochastic gradient descent, is an approach that injects noise into the gradients during the training phase. For the comparative study, we developed a multi-class classification architecture using a real-world, sensitive medical dataset derived from the MIMIC-IV database. Model performance was evaluated against a non-private baseline,
using the appropriate metrics considering our class imbalance, such as Macro F1-score and Macro OVO AUC. The results confirm the trade-off between privacy and utility in the models developed, where higher privacy guarantees consistently result in reduced model utility. For the specific context of this study, gradient perturbation provided a slightly more advantageous model in overall balance of utility and privacy. Ultimately, the thesis provides strong evidence for the feasibility of training useful and formally private machine learning models on real-world medical data, successfully demonstrating a practical "sweet spot" between privacy and performance can be found.
Description
Treballs Finals de Grau d'Enginyeria Informàtica, Facultat de Matemàtiques, Universitat de Barcelona, Any: 2025, Director: Nahuel Statuto
Subject (English)
Citation
Citation
MANTILLA CARREÑO, Juan Pablo. Differentially Private Machine Learning: Implementation and Analysis of Gradient and Dataset Perturbation Techniques. [consulted: 11 of June of 2026]. Available at: https://hdl.handle.net/2445/223909