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"”.
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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, …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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 …
-
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
-
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 …
-
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 …
-
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 …
Page 1 of 12