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 20 of 24 for “"Trustworthy AI"”.
-
Engineering data-sharing practices for a fair and trustworthy AI
… that ML applications are more likely to fail in identifying women than males in hospitals. Recent research has identified the data used to train these models as one of the causes of these issues. The research community has proposed guidelines to detect the dimensions that can generate …
-
Towards Trustworthy AI: Investigating Bias and Confidence Alignment in Large Language Models
… they express when queried about their certainty. This analysis is enriched by employing diverse datasets and prompting techniques aimed at encouraging model introspection, such as structured evaluation scales and the inclusion of answer options. Notably, OpenAI’s GPT-4 emerges as a leading …
-
Reliable and Trustworthy AI for Evidence-based Clinical Decision Support in Cancer Care
The integration of cutting-edge AI methods with real-world clinical data has moved from being a novelty to a necessity in oncology. However, the deployment of AI faces challenges, including the complexity of reliably modeling longitudinal Electronic Health Records (EHR) characterized by missing …
-
On Performance and Trustworthiness of AI: from inverse problems to Artificial General Intelligence
Artificial Intelligence (AI) has emerged as a powerful problem-solving tool, both in the mathematical field of inverse problems and, more recently, in broader applications with the advent of modern chatbots. However, AI systems have repeatedly been shown to be prone to producing hallucinations, …
-
Evaluating Trust in AI-Assisted Bridge Inspection through VR
The integration of Artificial Intelligence (AI) in collaborative tasks has gained momentum, with particular implications for critical infrastructure maintenance. This study examines the assurance goals of AI—security, explainability, and trustworthiness—within Virtual Reality (VR) environments for …
-
EFFORTS TOWARD TRUSTWORTHY MACHINE LEARNING: MITIGATING OVERCONFIDENCE, HALLUCINATION, AND MODALITY BIAS
Trustworthy machine learning is critical for safe deployment of AI systems in high-stakes domains. Despite strong performance, models remain prone to reliability issues such as overconfidence, hallucinations, and modality bias. This thesis addresses these challenges through post-hoc methods and …
-
Multiagent Approaches to Enhance Learning and Trust in AI Systems
… ensuring trust in real-world deployment. Many domains involve multiple adaptive agents interacting under uncertainty and limited information. To be effective, agents must adapt continuously while operating efficiently in large and complex decision spaces. Using frameworks such as extensive form …
-
Explainable Neural Claim Verification Using Rationalization
… which is a significant challenge. Although claim verification techniques exist, they lack proper explainability. Numerical scores such as Attention and Lime and visualization techniques such as saliency heat maps are insufficient because they require specialized knowledge. It is inaccessible …
-
Understanding and Improving Representational Robustness of Machine Learning Models
… we define as the “robustness” (or generally trustworthy properties) in the induced hidden space of a given network. For a generic representation network, this corresponds to the representation space itself, while for a smoothed model, we will treat the logits of the network as the target …
-
Machine Learning Methodologies for Beyond 5G and 6G Heterogeneous Networks: Prediction, Automation, and Performance Analysis
… authentication system. This system utilizes trustworthy AI and template obfuscation to ensure secure and confidential authentication, with excellent performance (ROC up to 0.99) and fast processing (1.47 seconds on average). Finally, a novel Energy Optimized Semantic Loss (EOSL) function is …
-
Neurosymbolic Reasoning for Link Prediction in Supply Chain Knowledge Graphs
… is motivated by recent developments in Supply Chain Management (SCM) and Artificial Intelligence (AI). On one side, as modern supply chains become complex and interconnected with invisible dependencies, we increasingly see disruptions emerging and propagating across the network. This phenomenon, …
-
Understanding and Mitigating Data-Centric Vulnerabilities in Modern AI Systems
Modern artificial intelligence (AI) systems, trained on vast internet-scale datasets, demonstrate remarkable performance and emergent capabilities. However, this reliance on large datasets that are expensive or difficult to quality-control exposes AI systems to critical vulnerabilities, including …
-
Trustworthy Reinforcement Learning under Constraints and Perturbations
… success in sequential decision making across domains such as game playing, autonomous driving, and large-scale resource allocation. However, deploying RL agents in real-world applications requires more than achieving high task performance, since it demands trustworthiness, encompassing safety, …
-
Robust and Efficient AI-models for Medical Image Reconstruction, Segmentation, and Multimodal Knowledge Distillation
Artificial intelligence (AI) is transforming the healthcare landscape, offering the promise of earlier diagnoses, more personalized treatments, and improved patient outcomes. However, despite its tremendous potential, deploying AI in real-world clinical settings remains fraught with challenges. …
-
SDP-CROWN: Efficient bound propagation for neural network verification with tightness of semidefinite programming
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms
-
Context-conscious fairness throughout the machine learning lifecycle
… increasingly used to inform decisions across domains, there has been a proliferation of literature seeking to define “fairness” narrowly as an error to be “fixed” and to quantify it as an algorithm’s deviation from a formalised metric of equality. Dozens of notions of fairness have been proposed, …
-
GREMLIN: GOES radar estimation via machine learning to inform NWP
… statistical tools, artificial intelligence (AI) / machine learning (ML) enables new approaches for connecting models and observations. The objective of this research is to develop techniques for assimilating GOES-R Series observations in precipitating scenes for the purpose of improving …
-
Human factors in the standardization of AI governance: Improving the design of risk management standards for ethical AI
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2025-10-19 without embargo terms
-
Trustworthy Soft Sensing in Water Supply Systems using Deep Learning
… conditions, calibration drift, high maintenance costs, and degrading. Researchers have turned to advanced computational methods, including mathematical modeling, statistical analysis, and machine learning, to overcome these limitations. Deep learning techniques have shown promise in …
-
Human-centric trustworthy foundation model reasoning
… convey information effectively. Advancements in AI have given rise to language models (LMs) being increasingly adopted in assisting information understanding and communication for different task settings. However, the potential that LMs can serve in supporting human communication is still …
Page 1 of 2