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 47 for “"Machine Learning Security"”.

  1. Assumption Stress-Testing for Machine Learning Security

    Security is guided by the principle that a system is only as strong as its weakest link. Despite the undeniable benefits brought by the growing integration of machine learning (ML) into nearly all aspects of modern life, decades of research and real-world deployment have established a broad …

    waterloo Repository record for Assumption Stress-Testing for Machine Learning Security (opens in a new tab)

  2. Evaluating and Mitigating Concept Drift in Machine Learning Security Tasks

    … to a degradation in the detection performance of machine learning models. As machine learning becomes increasingly prevalent in cybersecurity applications, the challenge of concept drift poses a significant threat to the long-term effectiveness of machine learning-based security systems. This …

    kings Repository record for Evaluating and Mitigating Concept Drift in Machine Learning Security Tasks (opens in a new tab) Download PDF for Evaluating and Mitigating Concept Drift in Machine Learning Security Tasks (opens in a new tab)

  3. An investigation of machine learning systems security with a forensics perspective

    Machine learning systems are increasingly deployed in security-critical environments, making it important not only to detect attacks but also to identify their source. Recent forensic tracing frameworks have been proposed to attribute adversarial examples to the models that generated them. However, …

    qu-belfast Repository record for An investigation of machine learning systems security with a forensics perspective (opens in a new tab) Download PDF for An investigation of machine learning systems security with a forensics perspective (opens in a new tab)

  4. An Interpretable Machine Learning Framework for Detecting Phishing URLs Based on Lexical Features

    … URLs that have not yet been catalogued in security databases. This research addresses this critical gap by developing an interpretable machine learning framework for detecting phishing URLs usingclexical, structural, content-based, and domain metadata features. The study employs a …

    rit Repository record for An Interpretable Machine Learning Framework for Detecting Phishing URLs Based on Lexical Features (opens in a new tab)

  5. Low-Overhead Techniques For Secure And Reliable Gpu Computing

    … the computations in various domains such as machine learning, security, financial and scientific computing. GPUs leverage the inherent data parallelism in the target applications to provide high throughput at superior energy efficiency. Due to the rising usage of GPUs for a large number of …

    wm-mary Repository record for Low-Overhead Techniques For Secure And Reliable Gpu Computing (opens in a new tab)

  6. Building Trustworthy Machine Learning Systems for Security: From Federated Learning to Agentic AI

    Federated Learning (FL) has emerged as a promising paradigm for privacy-preserving collaborative machine learning, enabling distributed devices to jointly train models without sharing raw data. This dissertation addresses critical challenges in building trustworthy and secure machine learning …

    vt Repository record for Building Trustworthy Machine Learning Systems for Security: From Federated Learning to Agentic AI (opens in a new tab)

  7. Game Theoretic Analysis of Defence Algorithms Against Data Poisoning Attack

    As Machine Learning (ML) algorithms are deployed to solve a wide variety of tasks in today’s world, data poisoning attack poses a significant threat to ML applications. Although numerous defence algorithms against data poisoning attack have been proposed and shown to be effective, most defence …

    mcmaster Repository record for Game Theoretic Analysis of Defence Algorithms Against Data Poisoning Attack (opens in a new tab)

  8. Towards Robust Deep Neural Networks

    … enable state-of-the-art performance for most machine learning tasks. Unfortunately, they are vulnerable to attacks, such as Trojans during training and Adversarial Examples at test time. Adversarial Examples are inputs with carefully crafted perturbations added to benign samples. In the …

    adelaide Repository record for Towards Robust Deep Neural Networks (opens in a new tab)

  9. On Using Embeddings for Ownership Verification of Graph Neural Networks

    Graph neural networks (GNNs) have emerged as a state-of-the-art approach to model and draw inferences from large scale graph-structured data in various application settings such as social networking. The primary goal of a GNN is to learn an embedding for each graph node in a dataset that encodes …

    waterloo Repository record for On Using Embeddings for Ownership Verification of Graph Neural Networks (opens in a new tab)

  10. Machine learning for security applications under dynamic and adversarial environments

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-03-01 without embargo terms

    uiuc Repository record for Machine learning for security applications under dynamic and adversarial environments (opens in a new tab)

  11. Certifiably trustworthy deep learning systems at scale

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-03-01 without embargo terms

    uiuc Repository record for Certifiably trustworthy deep learning systems at scale (opens in a new tab)

  12. Foresight: Countering Malware through Cooperative Forensics Sharing

    … epidemic nature of the spreads limits the time security experts have to respond and be able to protect and fortify their systems. A pathogen might infect thousands of machines and cascade across the network producing consequences that could overwhelm the internet very quickly. Such attacks have …

    duke Repository record for Foresight: Countering Malware through Cooperative Forensics Sharing (opens in a new tab)

  13. Adversarial and Data Poisoning Attacks against Deep Learning

    Machine translation software, image captioning, grammar check (Grammarly), chatbot, real-time captioning and translation, music genre classification, and document classification are a few examples of deep learning applications that achieve outstanding performance in areas where traditional …

    usf Repository record for Adversarial and Data Poisoning Attacks against Deep Learning (opens in a new tab)

  14. Antidistillation Sampling for Classification Models

    … to replicate the functionality of proprietary machine learning models by querying their APIs and training surrogate student models on the returned soft-label distributions. Antidistillation Sampling (ADS), recently proposed for large language models, perturbs the output distribution of a …

    rit Repository record for Antidistillation Sampling for Classification Models (opens in a new tab)

  15. From Image Enhancement to Model Protection Integrating Generative AI and Secure Learning in Computer Vision

    … challenges in the field of computer vision and machine learning, focusing on three key areas: image translation, denoising, and model security. The research encompasses novel methodologies and models that significantly advance existing techniques. This dissertation will not only provide valuable …

    odu Repository record for From Image Enhancement to Model Protection Integrating Generative AI and Secure Learning in Computer Vision (opens in a new tab)

  16. Generalised Defences Against Adversarial Attacks

    Machine learning (ML) models have revolutionised numerous fields, such as healthcare, finance, and transportation. However, this success comes with a cost, as concerns have emerged about the vulnerabilities of systems that rely on ML models. Adversarial attacks, where malicious actors intentionally …

    auckland-ms Repository record for Generalised Defences Against Adversarial Attacks (opens in a new tab)

  17. Advancing the Design and Utility of Adversarial Machine Learning Methods

    … of Adversarial Machine Learning techniques, which have remarkable abilities to both degrade and enhance model performance. Our ultimate goal is to help construct the more safe and reliable models of the future.</p><p>In the first thread of research, we take the …

    duke Repository record for Advancing the Design and Utility of Adversarial Machine Learning Methods (opens in a new tab)

  18. Machine learning approaches for malware classification based on hybrid artefacts

    … forms to deceive users and evade antivirus and security endpoint detection. Furthermore, if one machine in the network is compromised, it could be used for lateral movement--when malware spreads stealthily without sending an alarm to monitoring systems. Malware attacks pose security threats to …

    waikato-masters Repository record for Machine learning approaches for malware classification based on hybrid artefacts (opens in a new tab) Download file for Machine learning approaches for malware classification based on hybrid artefacts (opens in a new tab)

  19. Enhancing Proof-of-Learning Security Against Spoofing Attacks Using Model Watermarking

    With the rapid expansion of machine learning (ML) technologies across diverse domains such as healthcare, finance, and autonomous systems, ensuring secure and trustworthy training methodologies has become more critical than ever. Proof-of-Learning (PoL) has recently emerged as a foundational …

    embry-riddle Repository record for Enhancing Proof-of-Learning Security Against Spoofing Attacks Using Model Watermarking (opens in a new tab)

  20. Machine Learning and Big Data Approaches for Automatic Internet Monitoring

    L'abstract è presente nell'allegato / the abstract is in the attachment

    poli-torino Repository record for Machine Learning and Big Data Approaches for Automatic Internet Monitoring (opens in a new tab)

Page 1 of 3