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 30 for “"AI Security"”.

  1. Understanding, Fortifying and Democratizing AI Security

    As we steadily move towards an AI-powered utopia that could only be imagined in lofty fiction in the recent past, a formidable threat is emerging that endangers the acute capitalization of AI in our everyday lives. A growing body of adversarial machine learning research has revealed that deep …

    gatech Repository record for Understanding, Fortifying and Democratizing AI Security (opens in a new tab)

  2. The Evolution of AI Security : From Models to Agents

    Thesis (Ph.D.)--Michigan State University. Computer Science - Doctor of Philosophy, 2026

    msu Repository record for The Evolution of AI Security : From Models to Agents (opens in a new tab)

  3. AI Security Compliance and Testing Framework for Large Language Model Systems

    … workflows at a pace that has outrun the security frameworks designed to protect them. Conventional compliance standards such as SOC 2 and ISO 27001 provide no coverage for LLM-specific vulnerabilities including prompt injection, sensitive information disclosure, and system prompt leakage. …

    washington Repository record for AI Security Compliance and Testing Framework for Large Language Model Systems (opens in a new tab)

  4. AI Security Compliance and Risk Assessment Framework for Large Language Model Systems.

    … designed to oversee them. Standards such as NIST AI RMF 1.0 and ISO/IEC 42001 provide high-level principles for responsible AI but lack the operationalized, testable controls required for consistent compliance auditing of deployed LLM systems. This thesis designs, implements, and empirically …

    washington Repository record for AI Security Compliance and Risk Assessment Framework for Large Language Model Systems. (opens in a new tab)

  5. Towards Trustworthy AI: Computational Design Science Methods for AI Security and AI Alignment

    Artificial Intelligence (AI), particularly generative AI, has transformed many aspects of daily life. However, these advancements also bring significant challenges such as security vulnerabilities, fairness concerns, and alignment issues. On one hand, adversaries can exploit vulnerabilities in …

    arizona-thes Repository record for Towards Trustworthy AI: Computational Design Science Methods for AI Security and AI Alignment (opens in a new tab)

  6. From Adversarial Machine Learning to AI Security Risk: Applying Cybersecurity Methods to Artificial Intelligence

    … systems are increasingly deployed in security-relevant contexts, yet approaches to securing them remain fragmented across technical, organisational, and policy domains. Research in adversarial machine learning (AML) has shown that models can be manipulated, but this work is often …

    unsw Repository record for From Adversarial Machine Learning to AI Security Risk: Applying Cybersecurity Methods to Artificial Intelligence (opens in a new tab)

  7. 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 …

    vt Repository record for Evaluating Trust in AI-Assisted Bridge Inspection through VR (opens in a new tab)

  8. HARNESSING DEEP REINFORCEMENT LEARNING: STUDIES IN ROBOTIC MANIPULATION, ENHANCED SEMANTIC SEGMENTATION, AND SECURING IMAGE CLASSIFIERS

    … Learning (DRL) in three critical domains: robotic manipulation, enhanced semantic segmentation, and the security of image classifiers. Through comprehensive exploration and analysis, this research addresses the challenges and limitations inherent in current DRL methodologies, offering …

    oklahoma-thes Repository record for HARNESSING DEEP REINFORCEMENT LEARNING: STUDIES IN ROBOTIC MANIPULATION, ENHANCED SEMANTIC SEGMENTATION, AND SECURING IMAGE CLASSIFIERS (opens in a new tab) Restricted access

  9. Imagining the Impossible - Conflicting Norms and Values on Social Sustainability, Security, and Artificial Intelligence

    This thesis explores the relationship between AI, security, and social sustainability as a sociotechnical system, analyzing the implications and perspectives that arise from this understanding. It represents a culmination of four articles that rely on both conceptual insights and empirical …

    lund Repository record for Imagining the Impossible - Conflicting Norms and Values on Social Sustainability, Security, and Artificial Intelligence (opens in a new tab) Download PDF for Imagining the Impossible - Conflicting Norms and Values on Social Sustainability, Security, and Artificial Intelligence (opens in a new tab)

  10. Building Trustworthy Artificial Intelligence of Things Systems in Adversarial Environments

    … technologies. They have revolutionized people's daily lives, improving convenience, efficiency, and connectivity in previously unimaginable ways. Among all broad topics related to AI and IoT, the Artificial Intelligence of Things, abbreviated as AIoT, focuses specifically on the convergence of …

    vt Repository record for Building Trustworthy Artificial Intelligence of Things Systems in Adversarial Environments (opens in a new tab)

  11. Next-Gen AI: Advancing Watermarking, Algorithm Synthesis and Diverse Generative Strategies

    … in generative artificial intelligence (AI) across three domains: enhancing security through watermarking, advancing algorithm synthesis, and pioneering diverse strategies for generative image tasks. The research contributes novel methodologies and unified frameworks that push the …

    maryland Repository record for Next-Gen AI: Advancing Watermarking, Algorithm Synthesis and Diverse Generative Strategies (opens in a new tab)

  12. AI-Driven Penetration Testing for Arm Systems: A Comprehensive Framework With Experimental Validation

    … convergence of artificial intelligence and cybersecurity presents new opportunities for automated penetration testing capable of discovering, prioritizing, and remediating vulnerabilities at machine speed. However, deployment on resource-constrained ARM platforms remains unexplored despite ARM’s …

    gsu Repository record for AI-Driven Penetration Testing for Arm Systems: A Comprehensive Framework With Experimental Validation (opens in a new tab)

  13. 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 …

    vt Repository record for Understanding and Mitigating Data-Centric Vulnerabilities in Modern AI Systems (opens in a new tab)

  14. Adversarial robustness in advanced machine learning models integrating graph neural networks and large language models

    <p>Artificial intelligence (AI) has achieved remarkable performances across various domains. In most real-world applications, data often takes relational forms, such as graphs and networks, or sequential forms, such as text and time series. As AI evolves, specialized models have emerged to handle …

    njit Repository record for Adversarial robustness in advanced machine learning models integrating graph neural networks and large language models (opens in a new tab)

  15. Architectural Defenses for Agentic Systems: Prompt Injection and Beyond

    … this interaction: prompt injection and supply chain attacks. We propose architectural and deterministic defenses for these two problems. Firstly, we present a taxonomy of tasks based on the minimum data knowledge required for task completion by agents. Motivated by the fact that many tasks can be …

    vt Repository record for Architectural Defenses for Agentic Systems: Prompt Injection and Beyond (opens in a new tab)

  16. On the Security and Adaptation of Neural Networks: A Study of Adversarial Robustness, Backdoor Attacks, and Transfer Learning

    Neural networks have become the heart of modern AI systems, playing a crucial role in both commercial and critical applications. However, these models face two significant challenges: security vulnerabilities and adaptation to new test data and tasks. These models are vulnerable to various …

    jhu Repository record for On the Security and Adaptation of Neural Networks: A Study of Adversarial Robustness, Backdoor Attacks, and Transfer Learning (opens in a new tab)

  17. Blockchain for AI: Smarter Contracts to Secure Artificial Intelligence Algorithms

    … models to compute complex operations of naive Bayes, linear regression, decision trees, and neural network algorithms on Ethereum public test networks. The smart contracts achieve 95\% prediction accuracy compared to traditional programming language models, proving the soundness of the …

    unt Repository record for Blockchain for AI: Smarter Contracts to Secure Artificial Intelligence Algorithms (opens in a new tab)

  18. Defending the Dialog: Characterizing and Mitigating Harmful Fine-Tuning Attacks in Conversational AI

    Generative AI (GenAI), especially Large Language Models (LLMs), has transformed conversational AI, enabling chatbots that converse fluently across a wide range of topics and perform diverse downstream tasks. There is growing demand to customize chatbots for specific downstream applications, and …

    vt Repository record for Defending the Dialog: Characterizing and Mitigating Harmful Fine-Tuning Attacks in Conversational AI (opens in a new tab)

  19. Novel Neural Network Repair Methods for Data Privacy and Individual Fairness

    … the demand for models that are trustworthy, fair, and preserve privacy becomes paramount. Despite this, significant privacy, trust, fairness, and security risks exist that make these models untrustworthy. Deep neural networks are vulnerable to attacks that reveal private information about …

    waterloo Repository record for Novel Neural Network Repair Methods for Data Privacy and Individual Fairness (opens in a new tab)

  20. Deployment Concerns in Machine Learning Systems: Unintended Interactions and Accountability

    … (iv) adversarial and societal risks (e.g., security, privacy, safety, unfairness, poor transparency, misalignment, misinformation, and cyberattacks), and (v) enabling governance (e.g., verifying claims by practitioners, and regulatory compliance). I focus on two deployment concerns: …

    waterloo Repository record for Deployment Concerns in Machine Learning Systems: Unintended Interactions and Accountability (opens in a new tab)

Page 1 of 2