Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 16 of 16 for “"Private machine learning"”.
-
Secure and Private Machine Learning
In recent years, the advances of Machine Learning (ML) have led to its increased application within critical applications and on highly sensitive data. This drew attention to the aspects of ML security and privacy. ML models should operate correctly and not reveal sensitive data that they were …
-
Enabling accurate and private machine learning systems
Machine learning applications in fields where data is sensitive, such as healthcare and banking, face challenges due to the need to protect the privacy of participating users. Tools developed in the past decades that aim to address this challenge include differential privacy and federated learning. …
-
Perceptions and Practicalities for Private Machine Learning
… subjects' privacy. In this thesis I show that private computation, such as private machine learning, can increase end-users' acceptance of data sharing practices, but not unconditionally. There are many factors that influence end-users' privacy perceptions in this space; including the number of …
-
Secure and private machine learning in hardware
Machine learning (ML) has seen a tremendous rise in interest in recent years, with neural networks in particular gaining widespread adoption. ML models run on many types of hardware, ranging from low-power IoT devices to powerful GPUs and a plethora of dedicated accelerators. However, their …
-
Towards Standardized Evaluation in Differentially Private Image Classification: A Critical Approach
This thesis critically examines differentially private machine learning (DPML) in image classification, addressing recent critiques about the effectiveness of current techniques and the validity of existing benchmarks. We focus on three key questions: the accuracy of current benchmarks in measuring …
-
Revisiting Benchmarks for Privacy-Preserving Image Classification
… of data leakage. While DP has been effective in machine learning (ML), there are growing concerns about some common practices in differentially private machine learning (DP ML), particularly the reliance on non-private ML benchmarks to measure progress. Popular datasets like CIFAR-10, while …
-
Communication and Round Balanced Oblivious FSM Evaluation
… regarding performing computations over private data, both in homomorphic encryption, multi-party computation, and applications that put these to use. Herein we present a multiparty protocol for the private evaluation of a finite state machine. We motivate this by noting that many …
-
On the efficiency and privacy of foundation models
… We combine previous advances in differentially private machine learning and apply it to latent diffusion models (LDMs). Specifically, we use DP-SGD to train a subset of parameters in the attention modules of the model. We make comparisons with existing works using Fréchet inception distance …
-
Information Bottleneck Methods for Fairness and Privacy in Machine Learning
Designing machine learning algorithms that are accurate yet fair, not discriminating based on any sensitive attribute, and also private, not revealing users’ personal information, has become of paramount importance for society to accept the widespread use of artificial intelligence (AI) for …
-
Towards Honest, Practicable and Efficient Private Learning
… to accomplish useful tasks, like building machine learning models or generating realistic synthetic data, while maintaining Differential Privacy. Crucially, these operations must be conducted within a predetermined, strict limit, often referred to as the "privacy budget." This budget …
-
Secure and Private ML-based Cybersecurity Framework for Industrial Internet of Things (IIoT)
… concerns, this thesis introduces a secure and private machine learning-based framework for IIoT. This framework is designed to offer robust and comprehensive solutions to the security and privacy issues plaguing IIoT systems. The first component of the framework introduces an auditable …
-
Some Fundamental Machine Learning Problems in the Differential Privacy Model
Machine Learning has emerged as one of the most powerful tools for us to learn and extract useful information from big data. It plays a vital role in many applications, especially in those from social sciences, finance, medical sciences and genomics research. However, due to the existence of …
-
Understanding and mitigating privacy risk in machine learning systems
… years have witnessed a rapid development in machine learning systems and a widespread increase of machine learning applications. However, with the widespread adoption of machine learning, privacy issues have emerged. This thesis studies the privacy risk in modern machine learning systems in …
-
Machine learning techniques for the preservation of data privacy
Machine learning has been successfully applied in various domains in recent years. Still, its use is limited since training or testing data may contain sensitive information which cannot be shared with model owners due to privacy concerns. For example, healthcare providers may be bound by patient …
-
Advances in privacy-preserving machine learning
Building useful predictive models often involves learning from personal data. For instance, companies use customer data to target advertisements, online education platforms collect student data to recommend content and improve user engagement, and medical researchers fit diagnostic models to …
-
Impactos econômicos da covid-19 no mercado odontológico privado no Estado do RS : o desenvolvimento e avaliação de um app low code de data science no knime
Introdução: Nesta pesquisa foi construída uma aplicação de Ciência de Dados na plataforma Knime, para a investigação e análise dos impactos econômicos da COVID-19 durante os seus primeiros 16 meses da pandemia, em consultórios odontológicos privados do Estado brasileiro do Rio Grande do Sul (RS). …