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 145 for “"adversarial robustness"”.

  1. Wasserstein Adversarial Robustness

    … ``small, imperceptible'' perturbations known as adversarial attacks. While the majority of existing attacks focus on measuring perturbations under the $\ell_p$ metric, Wasserstein distance, which takes geometry in pixel space into account, has long been known to be a suitable metric for measuring …

    waterloo Repository record for Wasserstein Adversarial Robustness (opens in a new tab)

  2. Understanding Adversarial Robustness in Deep Learning

    This thesis studies the adversarial robustness of deep learning models. Our investigation covers various aspects of this phenomenon, including the development of two new defense algorithms, two new attack algorithms, a novel definition of hierarchical adversarial robustness, and an analysis of how …

    toronto-retro Repository record for Understanding Adversarial Robustness in Deep Learning (opens in a new tab)

  3. Improving additional adversarial robustness for classification

    … achieved remarkable success on classification, adversarial robustness is still a significant concern. There are now a series of approaches for designing adversarial examples and methods to defending against them. This paper consists of two projects. In our first work, we propose an approach by …

    wustl Repository record for Improving additional adversarial robustness for classification (opens in a new tab)

  4. Adversarial Robustness for Estimation and Alignment

    … To this end, we analyze robust models and adversarial inputs in a variety of settings. We explore statistical estimation under the adversarial setting of Wasserstein distribution shifts, where every data point may undergo a bounded perturbation. We analyze several statistical problems, …

    penn Repository record for Adversarial Robustness for Estimation and Alignment (opens in a new tab)

  5. Adversarial robustness of Bayesian neural networks

    … thesis puts forward methods for computing local robustness of probabilistic neural networks, specifically those resulting from Bayesian inference. In theory, applying Bayesian inference to the learning of neural network parameters carries the promise of solving many practically vexing problems …

    oxford Repository record for Adversarial robustness of Bayesian neural networks (opens in a new tab)

  6. Adversarial Robustness of Deep Learning Models

    … learning tasks but remain highly vulnerable to adversarial perturbations. Adversarial training (AT) and its variants aim to enhance robustness by incorporating adversarial examples into training. However, AT often leads to both standard and robust generalization issues, the causes of which …

    ottawa-retro Repository record for Adversarial Robustness of Deep Learning Models (opens in a new tab)

  7. ADVERSARIAL ROBUSTNESS IN DEEP LEARNING NLP SYSTEMS

    … applications have heightened the importance of adversarial attacks and defenses. Research shows text-based attacks can significantly reduce NLP model performance, while defensive strategies only partially counteract these effects, leaving ample room for improvement. Current attack methodologies …

    nus Repository record for ADVERSARIAL ROBUSTNESS IN DEEP LEARNING NLP SYSTEMS (opens in a new tab) Download file for ADVERSARIAL ROBUSTNESS IN DEEP LEARNING NLP SYSTEMS (opens in a new tab)

  8. TOWARDS ADVERSARIAL ROBUSTNESS OF DEEP VISION ALGORITHMS

    … networks have been shown to be vulnerable to adversarial perturbations in input data. The security issues of deep neural networks have thus come to the fore. It is imperative to comprehensively study the adversarial robustness of deep vision algorithms. This thesis focuses on the adversarial …

    nus Repository record for TOWARDS ADVERSARIAL ROBUSTNESS OF DEEP VISION ALGORITHMS (opens in a new tab) Download file for TOWARDS ADVERSARIAL ROBUSTNESS OF DEEP VISION ALGORITHMS (opens in a new tab)

  9. Improving adversarial robustness of machine learning models

    In this thesis, we focus on improving the robustness of Deep Neural Networks (DNNs) and aim to build robust defense methods. We identity three important factors of DNNs, including training data, representation learnings, and model deployment. We develop RanTrain, CDAD, and RAD respectively. …

    adelaide Repository record for Improving adversarial robustness of machine learning models (opens in a new tab)

  10. Constraining Robust Information Quantities Improves Adversarial Robustness

    … networks (DNNs) are vulnerable to imperceptible adversarial attacks, and this fact raises concerns about their safety and reliability in real-world applications. In this thesis, we aim to boost the robustness of DNNs against white-box adversarial attacks by defining three information quantities: …

    waterloo Repository record for Constraining Robust Information Quantities Improves Adversarial Robustness (opens in a new tab)

  11. On the adversarial robustness of Gaussian processes

    <p>We study the robustness of Bayesian inference with Gaussian processes (GP) under adversarial attack settings. We begin by noticing how the distinction between model prediction and decision in Bayesian settings naturally leads us to give two different notions of adversarial robustness. The …

    oxford Repository record for On the adversarial robustness of Gaussian processes (opens in a new tab)

  12. Adversarial Robustness and Fairness in Deep Learning

    … significant challenges such as vulnerability to adversarial attacks and model unfairness. These challenges have profound implications for privacy, security, and societal impact, requiring thorough investigation and development of effective mitigation strategies. In this work we address both these …

    maryland Repository record for Adversarial Robustness and Fairness in Deep Learning (opens in a new tab)

  13. Surveying the effects of data on adversarial robustness

    … and scalability. However, the vulnerability to adversarial examples, which are intentionally designed by attackers to confuse the models, impedes the adoption of them in life- and safety-critical applications. To address this problem, the area of adversarial robustness investigates the …

    ubc Repository record for Surveying the effects of data on adversarial robustness (opens in a new tab) Download PDF for Surveying the effects of data on adversarial robustness (opens in a new tab)

  14. Study on Adversarial Robustness of Phishing Email Detection Models

    … public phishing/legitimate datasets are lack adversarial email examples which keeps the detection models vulnerable. To address this problem, we developed an augmented phishing/legitimate email dataset, utilizing different adversarial text attack techniques. In this work, the emails that can …

    houston Repository record for Study on Adversarial Robustness of Phishing Email Detection Models (opens in a new tab)

  15. On the adversarial robustness of Bayesian machine learning models

    … is known about their vulnerability against adversarial attacks. Such attacks aim to cause undesired model behaviour (e.g. misclassification) by crafting small perturbations to regular inputs which appear to be insignificant to humans (e.g. slight blurring of image data). This fairly recent …

    oxford Repository record for On the adversarial robustness of Bayesian machine learning models (opens in a new tab)

  16. Adversarial robustness of deep learning enabled industry 4.0 prognostics

    … algorithms are known for their susceptibility to adversarial examples. Such adversarial attacks have been extensively studied in the computer vision domain. However, it is surprising that their impact on the PHM domain is yet not explored. Thus, modern data-driven intelligent PHM systems pose a …

    missouri Repository record for Adversarial robustness of deep learning enabled industry 4.0 prognostics (opens in a new tab)

  17. Adversarial Robustness and Robust Meta-Learning for Neural Networks

    … behave categorically different from humans. Adversarial examples, small perturbations which are often undetectable to the human eye, easily fool neural networks, demonstrating that neural networks lack the robustness of human classifiers. This thesis comprises a sequence of three parts. …

    maryland Repository record for Adversarial Robustness and Robust Meta-Learning for Neural Networks (opens in a new tab)

  18. Efficient Explainable AI And Adversarial Robustness using Formal Methods

    … biases or inconsistencies in predictions. Third, adversarial robustness is explored by integrating methods to generate and detect adversarial examples. These adversarial samples expose vulnerabilities in the model by identifying subtle input changes that lead to incorrect predictions. Detection …

    concordia Download PDF for Efficient Explainable AI And Adversarial Robustness using Formal Methods (opens in a new tab)

  19. Adversarial Robustness of Modular Autonomous Driving Agents for Lane Keeping

    … However, modularity does not necessarily imply robustness: adversarial perturbations can enter at multiple interfaces and propagate to downstream control. This thesis investigates adversarial robustness in a modular deep learning lane-keeping agent in the CARLA simulator, consisting of a learned …

    waterloo Repository record for Adversarial Robustness of Modular Autonomous Driving Agents for Lane Keeping (opens in a new tab)

Page 1 of 8