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"”.
-
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 …
-
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 …
-
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, …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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
-
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
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
Machine Learning and Big Data Approaches for Automatic Internet Monitoring
L'abstract è presente nell'allegato / the abstract is in the attachment
Page 1 of 3