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 15 of 15 for “"Secure AI"”.
-
Advancing Human-Computer Interaction Systems Through Explainable And Secure AI Integration
As artificial intelligence (AI) systems increasingly shape how humans interact with digital environments, the need for transparency, security, and robustness in intelligent decision making has become critical. This thesis explores how explainable and secure AI techniques can be integrated into …
-
Towards efficient and secure AI: Nearest Neighbor Algorithms for transformers and adversarial robustness
… the theoretical foundations of kNN attention remain underexplored. This work establishes a rigorous framework for kNN attention, reformulating self-attention as expectations over softmax distributions and leveraging lazy Gumbel sampling with kNN indices for efficient approximation. Building on …
-
ENHANCING PRIVACY WHILE REVEALING VULNERABILITIES: STRATEGIES FOR ADAPTATION, OPTIMIZATION, AND MODEL EXTRACTION
… critical areas: embracing semi-supervised domain adaptation for secure knowledge transfer, enhancing the model performance of tiny models, and executing model stealing attacks via diversified prompts. The overarching goal is to enhance the performance, scalability, and security of AI models …
-
Lamb: An advanced architecture for secure agents - Extending agentic AI utility while maintaining strong security guarantees through information flow control
… problem for the emerging technology of agentic AI. To mitigate them, existing deterministic agents rely on the Dual LLM pattern that disallows untrusted sources from influencing control flow. The pattern prevents execution of benign subtasks embedded within those sources, compromising agent …
-
HARNESSING ARTIFICIAL INTELLIGENCE FOR HUMAN INTELLIGENCE OPERATIONS
… the intersection of artificial intelligence (AI) and human intelligence (HUMINT), analyzing how AI can support and transform HUMINT operations. It reviews AI's benefits and explores opportunities and challenges of AI integration in intelligence collection. Examining the agent recruitment …
-
AN ANALYSIS OF SECURITY RISKS POSED BY TEXT-BASED GENERATIVE AI AND CORPORATE SECURITY WEAKNESSES LEADING TO DATA LEAKS
ABSTRACT Generative AI (GenAI) has become a fundamental part of modern life, influencing how we work, learn, and interact with technology. This project focuses specifically on text-based GenAI, which is widely used for tasks such as information gathering, code improvement, and content creation. …
-
Securing the Foundations of AI Through Reliable and Robust Arithmetic Units
… integrity of Artificial Intelligence (AI) accelerators is fundamentally tied to the reliability of their underlying arithmetic hardware. As modern computing substrates increasingly rely on high-throughput components like systolic arrays, the reliability and trustworthiness of these …
-
Security weaknesses in AI-generated code : a comparative analysis across models and programming languages : a thesis presented in partial fulfilment of the requirements for the degree of Master of Information Sciences in Software Engineering at Massey University, Palmerston North, New Zealand
The security of AI-generated code remains a major challenge for its widespread adoption. Code generation models have demonstrated strong performance on functional benchmarks. However, their outputs frequently contain bugs and security weaknesses that reduce their reliability in real-world settings. …
-
Improving the Reliability of AI Infrastructure Software with Data-Driven Software Analytics
Today, AI systems are increasingly used in safety-critical fields like transportation, finance, and robotics. While AI offers many benefits that simplify daily life, its widespread adoption has also increased threats, highlighting the urgent need for secure AI. Failing to protect AI systems against …
-
Robustness, Detectability, and Data Privacy In AI
… rapid advancements in Artificial Intelligence (AI) have made it widely popular in various applications, ranging from autonomous systems to multimodal content generation. However, these models are vulnerable to several security and safety problems. These pitfalls in AI models can potentially …
-
Towards Securing AI Systems: Investigating Threats in Multimodal Autonomous Driving & RAG Systems
Artificial Intelligence (AI) systems have become central to high-stakes applications such as autonomous driving and language-based decision support. As their deployment accelerates, ensuring the security and trustworthiness of these systems becomes paramount. Among the most stealthy and potent …
-
Integrating Artificial Intelligence for Transportation Cyber-Physical Systems: From Detection to Cyber Resilience
… warming. The first part of the dissertation aims to create a cost-effective system for real-time methane detection and intensity prediction using ensemble learning models trained on meteorological parameters. The ensemble learning-based classification models show a high accuracy for methane …
-
ACADIA: Efficient and Robust Adversarial Attacks Against Deep Reinforcement Learning
… attacks, called ACADIA, representing AttaCks Against Deep reInforcement leArning. ACADIA provides a set of efficient and robust perturbation-based adversarial attacks to disturb the DRL agent's decision-making based on novel combinations of techniques utilizing momentum, ADAM optimizer (i.e., …
-
Deep learning enhanced security for network-on-chip in heterogeneous computing systems
The rapid advancement of Artificial Intelligence (AI) has accelerated significantly in recent decades. Notable milestones include ImageNet, which established a benchmark for vision-based AI tasks, and Google DeepMind's AlphaGo defeating human players. Currently, Large Language Models (LLMs) such as …
-
The UAE’s Readiness For Technology Export: The case of AI
… diversification is one way for the UAE to sustain and flourish its economy. Although UAE is an oil-rich country, it needs to search for and incubate future exports besides the existing ones to keep the wheel of the economy moving, increase the employment rate, and strengthen the country from …