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 230 for “"adversarial training"”.

  1. MixUp as Directional Adversarial Training: A Unifying Understanding of MixUp and Adversarial Training

    … is a data augmentation scheme in which pairs of training samples and their corresponding labels are mixed using linear coefficients. Without label mixing, MixUp becomes a more conventional scheme: input samples are moved but their original labels are retained. Because samples are preferentially …

    ottawa-retro Repository record for MixUp as Directional Adversarial Training: A Unifying Understanding of MixUp and Adversarial Training (opens in a new tab)

  2. Monocular Depth Estimation using Adversarial Training

    … account global scene consistency. Generative Adversarial Networks(GANs) effectively capture the global structure of the scene and produce real-looking images, so they have the potential of depth estimation from a single image. This work focuses on using adversarial training for a supervised …

    umn Repository record for Monocular Depth Estimation using Adversarial Training (opens in a new tab)

  3. Fair and secure federated adversarial training

    Training machine learning models that are simultaneously private, robust, and deployable on resource-constrained edge devices requires resolving three tensions that have largely been treated in isolation. This thesis addresses all three through a unified sequence of contributions in Federated …

    ets-quebec Download PDF for Fair and secure federated adversarial training (opens in a new tab)

  4. Towards Robust Visual Classification through Adversarial Training

    … remarkable capabilities, they are vulnerable to adversarial examples. Adversarial examples are input data perturbed by the human-imperceptible noise to induce the wrong and/or malicious outcome of the victim model. The existence of such vulnerability raises severe concerns on the trustworthiness …

    kings Repository record for Towards Robust Visual Classification through Adversarial Training (opens in a new tab) Download PDF for Towards Robust Visual Classification through Adversarial Training (opens in a new tab)

  5. Multi-Domain Text Classification with Adversarial Training

    … domain-dependent task, a subtle shift between training and testing data distributions can cause catastrophic performance deterioration. Moreover, the availability of massive labeled data varies among different domains in real-world applications. Therefore, it is of great importance to …

    carleton Repository record for Multi-Domain Text Classification with Adversarial Training (opens in a new tab)

  6. Statistical and Computational Analysis of Adversarial Training

    Adversarial training is a powerful tool to hedge against data perturbations and distributional shifts, and has been widely used in large language models, computer vision, cybersecurity, etc. While the empirical risk minimization procedure optimizes the empirical loss, the adversarial training …

    gatech Repository record for Statistical and Computational Analysis of Adversarial Training (opens in a new tab)

  7. Towards Stable Adversarial Training with Stochastic Attention

    … between neural network performance on benign and adversarially altered data. Consequently, there is no clear consensus on how the optimization algorithms and network architectures should navigate this tradeoff. Further exacerbating the dilemma, defending ML models typically increase the overall …

    arizona-thes Repository record for Towards Stable Adversarial Training with Stochastic Attention (opens in a new tab)

  8. Adversarial Training and Computer Vision Methods for AI Robustness

    … by a vast amount of computing resources and training data, AI is reshaping human life. Despite their remarkable performance, the robustness issue of AI could pose serious challenges to their widespread deployment, especially in security-critical applications like autonomous driving and …

    jhu Repository record for Adversarial Training and Computer Vision Methods for AI Robustness (opens in a new tab)

  9. Adversarial training objectives for generative attacks on text classifiers

    In natural language processing, creating textual adversarial examples is challenging. These examples aim to deceive text classifiers into incorrect predictions while maintaining linguistic similarity to genuine inputs. This complexity arises from the need to preserve the original text's fluency, …

    uts Repository record for Adversarial training objectives for generative attacks on text classifiers (opens in a new tab)

  10. Adversarial training for machine learning classifiers against multiple adversaries

    … without affecting human perception. Traditional adversarial training techniques, which aim to enhance model robustness, typically treat all data points equally. This uni-form treatment does not account for the varying susceptibility of individual samples to adversarial perturbation. To address …

    vu-aus Download PDF for Adversarial training for machine learning classifiers against multiple adversaries (opens in a new tab)

  11. Adversarial Training for Skill Learning in a Mobile Robot

    … of large collaboratively-created labeled training datasets that researchers can use as the basis for experiments to validate and improve their candidate neural network architectures. For the field of robotics, however, tasks are so disparate and the physical devices so varied that in most …

    cuny-grad Repository record for Adversarial Training for Skill Learning in a Mobile Robot (opens in a new tab)

  12. Robust Dynamical Step Adversarial Training Defense for Deep Neural Networks

    … tasks, neural networks are still vulnerable to adversarial examples. Adversarial examples typically stay indistinguishable to human, while they can dramatically decrease the classifying accuracy of the neural network. Adversarial training generates such examples and train them together with the …

    tamu Repository record for Robust Dynamical Step Adversarial Training Defense for Deep Neural Networks (opens in a new tab)

  13. Understanding Adversarial Training: Improve Image Recognition Accuracy of Convolution Neural Network

    … neural networks, consistently misclassify adversarial examples—inputs formed by applying small but intentionally worst-case perturbations to examples from the dataset, such that the perturbed input results in the model outputting an incorrect answer with high confidence. The main purpose of …

    cuny Repository record for Understanding Adversarial Training: Improve Image Recognition Accuracy of Convolution Neural Network (opens in a new tab)

  14. Towards optimal trade-offs between accuracy and robustness in adversarial training

    … of deep neural networks (DNNs) against adversarial attacks while maintaining high performance on natural datasets. Despite significant advancements in adversarial training techniques, a considerable gap remains in effectively balancing the trade-offs between achieving high natural …

    iastate Repository record for Towards optimal trade-offs between accuracy and robustness in adversarial training (opens in a new tab)

  15. The Suitability of Generative Adversarial Training for BERT Natural Language Generation

    … was designed to test the effect of generative adversarial network (GAN) training on the quality of natural language generation (NLG) using a pre-trained language model architecture: Bidirectional Encoder Representations from Transformers (BERT). Perplexity and BLEU scores were used as metrics …

    washington Repository record for The Suitability of Generative Adversarial Training for BERT Natural Language Generation (opens in a new tab)

  16. Design and evaluation of GAN-based models for adversarial training robustness in deep learning

    Adversarial attacks show one of the generalization issues of current deep learning models on special distribution shifted data. The adversarial samples generated by the attack algorithm can introduce malicious behavior to any deep learning system that affects the consistency of the deep learning …

    uoit Repository record for Design and evaluation of GAN-based models for adversarial training robustness in deep learning (opens in a new tab)

  17. Improved pose estimation accuracy of monocular deep visual odometry against dynamic entities via adversarial training

    Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms

    uiuc Repository record for Improved pose estimation accuracy of monocular deep visual odometry against dynamic entities via adversarial training (opens in a new tab)

  18. A Transfer Learning Framework for Self-Adaptive Intrusion Detection in the Smart Grid based on Transferability Analysis and Domain-Adversarial Training

    … grid. General ML approaches presume that the training and testing data are generated by identical or similar independent distribution. This assumption may not hold in many real-world systems and applications like the CPS, since the system and attack dynamics may change the data distribution …

    concordia Download PDF for A Transfer Learning Framework for Self-Adaptive Intrusion Detection in the Smart Grid based on Transferability Analysis and Domain-Adversarial Training (opens in a new tab)

  19. Evaluating Methods for Improving DNN Robustness Against Adversarial Attacks

    … confidence. Those kinds of images are called adversarial attacks. Adversarial training has been developed to defend against adversarial attacks. This thesis evaluates different adversarial training methods against a variety of adversarial attacks. The key metrics for evaluation are …

    usf Repository record for Evaluating Methods for Improving DNN Robustness Against Adversarial Attacks (opens in a new tab)

  20. Enhancing Resilience Against Adversarial Attacks of Deep Neural Networks Using Efficient Two-Step Adversarial Defense

    … these state-of-the-art models are vulnerable to adversarial examples: legitimate examples added by small perturbations which are unnoticeable to human eyes. Adversarial training, which augments the training data with adversarial examples during the training process, is a well known defense to …

    tamu Repository record for Enhancing Resilience Against Adversarial Attacks of Deep Neural Networks Using Efficient Two-Step Adversarial Defense (opens in a new tab)

Page 1 of 12