A Gaussian Data Augmentation Technique on Highly Dimensional, Limited Labeled Data for Multiclass Classification Using Deep Learning

Rochac, Juan F. Ramirez; Liang, Lily R.; Zhang, Nian; Oladunni, Timothy

doi:10.1109/icicip47338.2019.9012197

Cited by 6 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…are used for diversifying the training data and increasing its size. In addition, different transformation techniques are used for augmenting training datasets, e.g., use of Gaussian for data augmentation [90], [91]. However, the use of data augmentation might reduce the robustness of the developed ML/DL based system, for example, it is highly likely that the distribution of transformed data diverges from the underlying actual distribution of the training data which is unknown generally and there are no statistical and probabilistical guarantees for having same distribution of the training data.…”

Section: A Sources Of Vulnerabilities In ML Pipelinementioning

confidence: 99%

Secure and Robust Machine Learning for Healthcare: A Survey

Qayyum

Qadir

Bilal

et al. 2021

IEEE Rev. Biomed. Eng.

385

144

View full text Add to dashboard Cite

Recent years have witnessed widespread adoption of machine learning (ML)/deep learning (DL) techniques due to their superior performance for a variety of healthcare applications ranging from the prediction of cardiac arrest from onedimensional heart signals to computer-aided diagnosis (CADx) using multi-dimensional medical images. Notwithstanding the impressive performance of ML/DL, there are still lingering doubts regarding the robustness of ML/DL in healthcare settings (which is traditionally considered quite challenging due to the myriad security and privacy issues involved), especially in light of recent results that have shown that ML/DL are vulnerable to adversarial attacks. In this paper, we present an overview of various application areas in healthcare that leverage such techniques from security and privacy point of view and present associated challenges. In addition, we present potential methods to ensure secure and privacy-preserving ML for healthcare applications. Finally, we provide insight into the current research challenges and promising directions for future research.

show abstract

Section: A Sources Of Vulnerabilities In ML Pipelinementioning

confidence: 99%

Secure and Robust Machine Learning for Healthcare: A Survey

Qayyum

Qadir

Bilal

et al. 2021

IEEE Rev. Biomed. Eng.

385

144

View full text Add to dashboard Cite

show abstract

“…The dataset can either be augmented with the new samples, or replaced by them. If used during the prediction phase, the Gaussian noise is added to the input before it is passed into the model for prediction [8].…”

Section: Defensesmentioning

confidence: 99%

Evaluation of Defense Methods Against the One-Pixel Attack on Deep Neural Networks

Arvidsson,

Al-Mashahedi,

Boldt

2023

Linköping Electronic Conference Proceedings

View full text Add to dashboard Cite

The one-pixel attack is an image attack method for creating adversarial instances with minimal perturbations, i.e., pixel modification. The attack method makes the adversarial instances difficult to detect as it only manipulates a single pixel in the image. In this paper, we study four different defense approaches against adversarial attacks, and more specifically the one-pixel attack, over three different models. The defense methods used are: data augmentation, spatial smoothing, and Gaussian data augmentation used during both training and testing. The empirical experiments involve the following three models: all convolutional network (CNN), network in network (NiN), and the convolutional neural network VGG16. Experiments were executed and the results show that Gaussian data augmentation performs quite poorly when applied during the prediction phase. When used during the training phase, we see a reduction in the number of instances that could be perturbed by the NiN model. However, the CNN model shows an overall significantly worse performance compared to no defense technique. Spatial smoothing shows an ability to reduce the effectiveness of the one-pixel attack, and it is on average able to defend against half of the adversarial examples. Data augmentation also shows promising results, reducing the number of successfully perturbed images for both the CNN and NiN models. However, data augmentation leads to slightly worse overall model performance for the NiN and VGG16 models. Interestingly, it significantly improves the performance for the CNN model. We conclude that the most suitable defense is dependent on the model used. For the CNN model, our results indicate that a combination of data augmentation and spatial smoothing is a suitable defense setup. For the NiN and VGG16 models, a combination of Gaussian data augmentation together with spatial smoothing is more promising. Finally, the experiments indicate that applying Gaussian noise during the prediction phase is not a workable defense against the one-pixel attack.

show abstract