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 12 of 12 for “"Privacy-preserving AI"”.
-
Input Structure Based Optimization for Privacy Preserving AI Systems
As Artificial Intelligence (AI) systems become increasingly integrated into critical domains, ensuring privacy-preserving model design and system deployment has become a pressing priority. Safeguarding both sensitive user data and proprietary model parameters is critical throughout the AI model and …
-
DESIGN METHODOLOGIES FOR TRUSTED AND EFFICIENT OUTSOURCING OF PRIVACY-PRESERVING AI
… data breaches and the recently introduced data privacy regulations worldwide have motivated concentrated research efforts to develop secure and efficient privacy-preserving technologies, impacting several vital domains, such as healthcare, finance, and manufacturing. Privacy-preserving …
-
A Privacy-Preserving, AI-Driven Framework For Bathroom Activity Monitoring And Health Recommendation In Elderly Care
… solutions, for monitoring Activities of Daily Living (ADLs) to detect early signs of health decline. This thesis presents a novel, end-to-end framework for monitoring bathroom activities—specifically bathing, toileting, and oral hygiene—using wearable sensors, machine learning and Agentic …
-
Privacy-Preserving AI for Mental Wellbeing Monitoring: From Passive Sensing to Online Engagement, through a User-Centred Lens
… traditional approaches<br/>to monitoring it remain episodic, burdensome, and poorly suited for detecting day-to-day<br/>fluctuations. The rise of smartphones, wearables, and online platforms enables continuous<br/>collection of behavioural and physiological signals, ranging from activity, sleep, …
-
Efficient model adaptation and compression for edge intelligence
… remarkable success through large-scale pre-training of language and vision models, followed by task-specific adaptation. However, deploying such models on mobile and edge platforms remains challenging due to the limited memory capacity and shared computational resources inherent to these …
-
Trustworthy AI for Smart Systems: Ensuring Resilience, Sustainability, and Responsibility in Autonomous Decision-Making
… potential in enhancing efficiency, sustainability, and decision-making. However, this proliferation also raises pressing concerns around trustworthiness, privacy, resilience, and ethical use of AI technologies. This dissertation investigates the foundational principles and practical …
-
Software Architecture Design for Federated Learning Systems
… deep learning and machine learning as the subdomain of AI have been demonstrated in multiple industries. However, the requirement for data by deep machine learning models has raised data privacy concerns. For instance, the EU's General Data Protection Regulation (GDPR) stipulates a range of data …
-
MACHINE UNLEARNING IN GRAPHS, RECOMMENDATIONS, AND LANGUAGE MODELS
… addressing critical challenges related to data privacy, ethical compliance, and adaptability in dynamic environments. The rapid advancements in this field have intensified concerns over these issues, necessitating the development of machine unlearning—techniques that enable models to selectively …
-
Design of Next-Generation Hardware-Accelerated Edge AI Engines for Privacy Preservation}
Artificial Intelligence (AI) has become ubiquitous across domains such as healthcare, finance, and autonomous systems, where it routinely processes sensitive personal and organizational data. This widespread adoption raises urgent concerns about model leakage, inference attacks, and the …
-
A 3d-enabled visual representation tool as a progressive web application (PWA) based on the WebAssembly specification
… cloud-based ecosystem that integrates AI-powered vascular segmentation, real-time 3D visualization, and predictive modeling for PAD risk assessment and treatment planning. The first chapter provides a detailed introduction to PAD, its pathophysiology, and the limitations of current …
-
Nova: Privacy-Preserving Goal-Oriented Reasoning in Smart Homes with On-Device Vision-Language Models
… interdependent human and device actions, and sustained multi-turn interaction to progressively transition the environment from an initial state to a desired state. Current systems are ill-equipped for this class of tasks, as they lack the ability to reason visually about the space or engage users …
-
From neural networks to large language models: innovations in financial ai, mathematical reasoning, and structured data representation
… intelligence techniques across three critical domains: financial modeling, mathematical reasoning, and structured data analysis. The dissertation presents seven research projects that chart a progression from specialized neural architectures to sophisticated large language models (LLMs), …