RoCGAN: Robust Conditional GAN

Chrysos, Grigorios; Kossaifi, Jean; Zafeiriou, Stefanos

doi:10.1007/s11263-020-01348-5

Cited by 19 publications

(8 citation statements)

References 38 publications

(44 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To further optimize our GNDA-based DCSAM, we plan to investigate the following issues: To balance the class, we will first try to use the dual-pipeline mechanism of Robust Conditional Generative Adversarial Network (RoCGAN) [ 81 ] to simulate sleep data at the N1 stage and expand the data, or we will attempt to implement ensemble and transfer learning [ 82 , 83 ], i.e., use relevant knowledge about sleep from training a large public dataset to facilitate the learning of sleep features in a new dataset. The data-driven DNN models are widely used to classify sleep stages and can achieve a reasonable performance.…”

Section: Discussionmentioning

confidence: 99%

Sleep Stage Classification in Children Using Self-Attention and Gaussian Noise Data Augmentation

Huang

Shirahama

Irshad

et al. 2023

Sensors

View full text Add to dashboard Cite

The analysis of sleep stages for children plays an important role in early diagnosis and treatment. This paper introduces our sleep stage classification method addressing the following two challenges: the first is the data imbalance problem, i.e., the highly skewed class distribution with underrepresented minority classes. For this, a Gaussian Noise Data Augmentation (GNDA) algorithm was applied to polysomnography recordings to seek the balance of data sizes for different sleep stages. The second challenge is the difficulty in identifying a minority class of sleep stages, given their short sleep duration and similarities to other stages in terms of EEG characteristics. To overcome this, we developed a DeConvolution- and Self-Attention-based Model (DCSAM) which can inverse the feature map of a hidden layer to the input space to extract local features and extract the correlations between all possible pairs of features to distinguish sleep stages. The results on our dataset show that DCSAM based on GNDA obtains an accuracy of 90.26% and a macro F1-score of 86.51% which are higher than those of our previous method. We also tested DCSAM on a well-known public dataset—Sleep-EDFX—to prove whether it is applicable to sleep data from adults. It achieves a comparable performance to state-of-the-art methods, especially accuracies of 91.77%, 92.54%, 94.73%, and 95.30% for six-stage, five-stage, four-stage, and three-stage classification, respectively. These results imply that our DCSAM based on GNDA has a great potential to offer performance improvements in various medical domains by considering the data imbalance problems and correlations among features in time series data.

show abstract

Section: Discussionmentioning

confidence: 99%

Sleep Stage Classification in Children Using Self-Attention and Gaussian Noise Data Augmentation

Huang

Shirahama

Irshad

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…RoCGAN: Chrysos et al [81] focused on conditional GANs (cGAN) [75], which generate samples conditioned on labels by providing additional labels, e.g., a prior shape [82] or an embedded representation [75]. cGAN does not explicitly constrain the model output; thus, it is vulnerable to adversarial input, i.e., evasion attacks.…”

Section: Change Model Architecturementioning

confidence: 99%

Adversarial Attacks Against Deep Generative Models on Data: A Survey

Sun

Zhu

Zhang

et al. 2023

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

Deep generative models have gained much attention given their ability to generate data for applications as varied as healthcare to financial technology to surveillance, and many more -the most popular models being generative adversarial networks (GANs) and variational auto-encoders (VAEs). Yet, as with all machine learning models, ever is the concern over security breaches and privacy leaks and deep generative models are no exception. In fact, these models have advanced so rapidly in recent years that work on their security is still in its infancy. In an attempt to audit the current and future threats against these models, and to provide a roadmap for defense preparations in the short term, we prepared this comprehensive and specialized survey on the security and privacy preservation of GANs and VAEs. Our focus is on the inner connection between attacks and model architectures and, more specifically, on five components of deep generative models: the training data, the latent code, the generators/decoders of GANs/VAEs, the discriminators/encoders of GANs/VAEs, and the generated data. For each model, component and attack, we review the current research progress and identify the key challenges. The paper concludes with a discussion of possible future attacks and research directions in the field.

show abstract

“…The most classical algorithm for image-to-image translation is the pix2pix method [18]. The pix2pix method introduces Conditional GAN (cGAN) as a general-problem solution, the model that can be trained not only by learning the mapping from input images to output images, but also by learning loss functions to tune the model [27].…”

Section: ) Generative Adversarial Networkmentioning

confidence: 99%

Conditional Generative Adversarial Network-Based Image Denoising for Defending Against Adversarial Attack

Zhang¹,

Sakurai

2021

IEEE Access

View full text Add to dashboard Cite

Deep learning has become one of the most popular research topics today. Researchers have developed cutting-edge learning algorithms and frameworks around deep learning, applying them to a wide range of fields to solve real-world problems. However, we are more concerned about the security risks associated with deep learning models themselves-such as adversarial attacks, which will be discussed in this article. Attackers can use the deep learning model to create the conditions for an attack, maliciously manipulating the input images to deceive the classification model and produce false positives. This paper proposes a method of pre-denoising all input images to prevent adversarial attacks by adding a purification layer before the classification model. The method in this paper is proposed based on the basic architecture of Conditional Generative Adversarial Networks. It adds the image perception loss to the original algorithm Pix2pix to achieve more efficient image recovery. Our method can recover noise-attacked images to a level close to the actual image to ensure the correctness of the classification results. Experimental results show that our approach can quickly recover noisy images, and the recovery accuracy is 20.22% higher than the previous state-of-the-art.

show abstract

RoCGAN: Robust Conditional GAN

Cited by 19 publications

References 38 publications

Sleep Stage Classification in Children Using Self-Attention and Gaussian Noise Data Augmentation

Sleep Stage Classification in Children Using Self-Attention and Gaussian Noise Data Augmentation

Adversarial Attacks Against Deep Generative Models on Data: A Survey

Conditional Generative Adversarial Network-Based Image Denoising for Defending Against Adversarial Attack

Contact Info

Product

Resources

About