A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Filters
Regularizing Generative Adversarial Networks under Limited Data
[article]
2021
arXiv
pre-print
Preserved Fulltext
Recent years have witnessed the rapid progress of generative adversarial networks (GANs). However, the success of the GAN models hinges on a large amount of training data. ...
We theoretically show a connection between the regularized loss and an f-divergence called LeCam-divergence, which we find is more robust under limited training data. ...
Related Work Generative adversarial networks. Generative adversarial networks (GANs) [2, 7, 14, 27, 32, 47, 79] aim to model the target distribution using adversarial learning. ...
arXiv:2104.03310v1
fatcat:b5th6vdcafgc5ostnr64xdzpte
Demotivate adversarial defense in remote sensing
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
In this work, we study both adversarial retraining and adversarial regularization as adversarial defenses to this purpose. ...
their ability to deal with the inherent variety of worldwide data. ...
This is an issue for both high resolution datasets which cover limited areas due to the cost of data and for low resolution datasets which either deal with high level label only or cover limited areas ...
arXiv:2105.13902v1
fatcat:2tb2zvyqxrfgbklhl56lhyejyi
Regularization by Adversarial Learning for Ultrasound Elasticity Imaging
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In this method, the regularizer is trained based on the Wasserstein Generative Adversarial Network (WGAN) objective function which tries to distinguish the distribution of clean and noisy images. ...
coping with the limited training data. ...
Since adversarial regularizers are trained based on image distribution loss, rather than image pixel loss, no paired training data is necessary. ...
arXiv:2106.00167v2
fatcat:v7mvvuwdtneuvg34wj3mryrhzm
Advanced Single Image Resolution Upsurging Using A Generative Adversarial Network
2020
Signal & Image Processing An International Journal
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2006.00186v1 fatcat:ttgiu3bogbf63gbmwfqrk6476y
In this paper, we have proposed a technique of generating higher resolution images form lower resolution using Residual in Residual Dense Block network architecture with a deep network. ...
In recent times, various research works are performed to generate a higher resolution of an image from its lower resolution. ...
different, BN layers limit the generation ability. ...
doi:10.5121/sipij.2020.11105
fatcat:cn2cifwd5bcsfezjeopmet47ru
Manifold Regularization for Locally Stable Deep Neural Networks
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We apply concepts from manifold regularization to develop new regularization techniques for training locally stable deep neural networks. ...
Our regularizers are based on a sparsification of the graph Laplacian which holds with high probability when the data is sparse in high dimensions, as is common in deep learning. ...
Applying the regularization term in Equation 2 yields, in the limit, a function which is smooth on the data manifold. ...
arXiv:2003.04286v2
fatcat:7v5tuul45vgy7jiljtannwg6um
Adversarial Training is a Form of Data-dependent Operator Norm Regularization
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We establish a theoretical link between adversarial training and operator norm regularization for deep neural networks. ...
Specifically, we prove that ℓ_p-norm constrained projected gradient ascent based adversarial training with an ℓ_q-norm loss on the logits of clean and perturbed inputs is equivalent to data-dependent ( ...
Data-dependent Operator Norm Regularization More generally, we can directly regularize the data-dependent pp, qq-operator norm of the Jacobian. ...
arXiv:1906.01527v5
fatcat:mgyc74zv4bacjisy35yxkipmyu
An Empirical Study on the Relation between Network Interpretability and Adversarial Robustness
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:1912.03430v5 fatcat:lsykrasakvbkhe6ifksyjvnyj4Other Versions
Applying the network interpretation technique SmoothGrad yields additional performance gains, especially in cross-norm attacks and under heavy perturbations. ...
We demonstrate that training the networks to have interpretable gradients improves their robustness to adversarial perturbations. ...
Minimizing degradation requires the norm of the Jacobian matrix to be small, whereas high generation performance requires the Jacobian to capture data regularities. ...
arXiv:1912.03430v6
fatcat:iidb5bqjgvf4vnszt3ruy25eem
An Empirical Study on the Relation Between Network Interpretability and Adversarial Robustness
2021
SN Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Applying the network interpretation technique SmoothGrad [59] yields additional performance gains, especially in cross-norm attacks and under heavy perturbations. ...
We demonstrate that training the networks to have interpretable gradients improves their robustness to adversarial perturbations. ...
Data Availability Statement All data and materials we used for our experiments are freely available via PyTorch's torchvision package [50] . ...
doi:10.1007/s42979-020-00390-x
fatcat:raovh7donna55gu7wlmygfc4qy
Enhancing MR Image Segmentation with Realistic Adversarial Data Augmentation
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 pre-print arXiv:2108.03429v1 fatcat:3dsqshzlbrc7lbmeujqpekblr4
The proposed adversarial data augmentation does not rely on generative networks and can be used as a plug-in module in general segmentation networks. ...
To address this challenge, we propose AdvChain, a generic adversarial data augmentation framework, aiming at improving both the diversity and effectiveness of training data for medical image segmentation ...
Augmenting images with these adversarial transformations contribute to stronger consistency regularization to enforce the network to be invariant under photometric transformations and equivariant under ...
arXiv:2108.03429v2
fatcat:m24wykdkbna3fdtq2t5qdlgq2i
Review of Artificial Intelligence Adversarial Attack and Defense Technologies
2019
Applied Sciences
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Finally, we describe the existing adversarial defense methods respectively in three main categories, i.e., modifying data, modifying models and using auxiliary tools. ...
However, artificial intelligence systems are vulnerable to adversarial attacks, which limit the applications of artificial intelligence (AI) technologies in key security fields. ...
[8] used a regularization method to limit the vulnerability of data when training an SVM model. ...
doi:10.3390/app9050909
fatcat:u4if4uweqzc6tfdrc3kokckkua
Adversarial Perturbations Fool Deepfake Detectors
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
The DIP defense removes perturbations using generative convolutional neural networks in an unsupervised manner. ...
This work uses adversarial perturbations to enhance deepfake images and fool common deepfake detectors. ...
CODE AVAILABILITY Code and additional architecture details are available at: https://github.com/ApGa/adversarial deepfakes. ...
arXiv:2003.10596v2
fatcat:h24oggx2tzd7tnkycyxr23xcaa
Infer-AVAE: An Attribute Inference Model Based on Adversarial Variational Autoencoder
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
not limited by observations. ...
data. ...
National Natural Science Foundation (U1736205, 61833015, U1766215, U1936110, 61902308) , the Fundamental Research Funds for the Central Universities (xzy012019036) , Foundation of Xi'an Jiaotong University under ...
arXiv:2012.15005v2
fatcat:rfawvt3vsvbj5lrrnx2wtmidaa
Defending Against Adversarial Attack in ECG Classification with Adversarial Distillation Training
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
, Jacob regularization, and noise-to-signal ratio regularization. ...
Deep neural networks (DNNs) can be used to analyze these signals because of their high accuracy rate. ...
Generally, PGD creates adversarial samples by using multiple iterations and limits the difference between new adversarial samples and those created in the last iteration. ...
arXiv:2203.09487v1
fatcat:aqduqnmembg7feirynvkzhgjs4
Multi-Class Triplet Loss With Gaussian Noise for Adversarial Robustness
2020
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
on both clean and adversarial data. ...
The ALP method matches the logits from clean image and it's corresponding adversarial image and provide an extra regularization term for better representation of the data. ...
doi:10.1109/access.2020.3024244
fatcat:fu2d7zmpmng53ojr65ximucqv4
Bridging the Gap Between Adversarial Robustness and Optimization Bias
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We demonstrate that the choice of optimizer, neural network architecture, and regularizer significantly affect the adversarial robustness of linear neural networks, providing guarantees without the need ...
for adversarial training. ...
For linearly separable data, under conditions of Theorem 4.1, the sequence of solutions to regularized classification problems converges in direction to a maximally robust classifier. ...
arXiv:2102.08868v2
fatcat:qhty2vogyvdmzaza45yr2xpq4y
« Previous
Showing results 1 — 15 out of 43,458 results