Filters








2,770 Hits in 4.5 sec

A Survey on Data-Driven Learning for Intelligent Network Intrusion Detection Systems

Ghada Abdelmoumin, Jessica Whitaker, Danda B. Rawat, Abdul Rahman
2022 Electronics  
It surveys and synthesizes generative-based data augmentation techniques for addressing the uneven data distribution and generative-based adversarial techniques for generating synthetic yet realistic data  ...  Hence, there is a need to train AN-Intel-IDS using dynamically generated, real-time data in an adversarial setting.  ...  Acknowledgments: We thank the Multidisciplinary Digital Publishing Institute (MDPI) for the opportunity to publish our work and for their generous support.  ... 
doi:10.3390/electronics11020213 fatcat:ej2mjxxghrhurfz2cz4pxaszaq

Data Augmentation in Emotion Classification Using Generative Adversarial Networks [article]

Xinyue Zhu, Yifan Liu, Zengchang Qin, Jiahong Li
2017 arXiv   pre-print
In this paper, we propose a data augmentation method using generative adversarial networks (GAN). It can complement and complete the data manifold and find better margins between neighboring classes.  ...  Empirical results show that we can obtain 5 classification accuracy after employing the GAN-based data augmentation techniques.  ...  In this research, based on Generative Adversarial Networks (GANs), we propose a new method for data augmentation in order to generate new samples via adversarial training, thus to supplement the data manifold  ... 
arXiv:1711.00648v5 fatcat:jcofsmztk5hlrnr3ypbocveya4

Generative Adversarial Network for Class-Conditional Data Augmentation

Jeongmin Lee, Younkyoung Yoon, Junseok Kwon
2020 Applied Sciences  
We propose a novel generative adversarial network for class-conditional data augmentation (i.e., GANDA) to mitigate data imbalance problems in image classification tasks.  ...  Experimental results demonstrate that the proposed GANDA can considerably improve classification accuracy, especially when datasets are highly imbalanced on standard benchmark datasets (i.e., MNIST and  ...  In this paper, we solve the data imbalance problem for image classification tasks and propose a novel data augmentation method based on GANs (i.e., generative adversarial network for class-conditional  ... 
doi:10.3390/app10238415 fatcat:3d5aymtbgbgvnnc6kazsy5s7pi

Handling Imbalanced Data in Intrusion Detection Systems using Generative Adversarial Networks

Ly Vu, Quang Uy Nguyen
2020 Research and Development on Information and Communication Technology  
In this paper, we propose a novel solution to thisproblem by using generative adversarial networks to generatesynthesized attack data for IDS.  ...  Subsequently, IDS datasets areoften dominated by normal data and machine learning modelstrained on those imbalanced datasets are ineffective in detect-ing attacks.  ...  SUMMARY In this paper, we proposed a novel approach based on generative adversarial networks for addressing imbalanced datasets in IDS.  ... 
doi:10.32913/mic-ict-research.v2020.n1.894 fatcat:yg4u6ebdd5abrldxxi5uxpu7pq

BAGAN: Data Augmentation with Balancing GAN [article]

Giovanni Mariani, Florian Scheidegger, Roxana Istrate, Costas Bekas, Cristiano Malossi
2018 arXiv   pre-print
In this work we propose balancing GAN (BAGAN) as an augmentation tool to restore balance in imbalanced datasets.  ...  The generator in the GAN is initialized with the encoder module of an autoencoder that enables us to learn an accurate class-conditioning in the latent space.  ...  The underlying idea is to train a generative network in adversarial mode against a discriminator network.  ... 
arXiv:1803.09655v2 fatcat:qbramjshfvbz3ap5qwa6nmhc6a

A comparative analysis of CGAN‐based oversampling for anomaly detection

Rahbar Ahsan, Wei Shi, Xiangyu Ma, William Lee Croft
2021 IET Cyber-Physical Systems  
This solution integrates the auto-learning ability of Reinforcement Learning with the oversampling ability of a Conditional Generative Adversarial Network (CGAN).  ...  In this work, the problem of anomaly detection in imbalanced datasets, framed in the context of network intrusion detection is studied.  ...  F I G U R E 1 Flow of data through the generative adversarial networks model  ... 
doi:10.1049/cps2.12019 fatcat:u6sos6phfrg7rjo5xivc6pspqq

Deep Adversarial Learning in Intrusion Detection: A Data Augmentation Enhanced Framework [article]

He Zhang, Xingrui Yu, Peng Ren, Chunbo Luo, Geyong Min
2019 arXiv   pre-print
Those synthesised data are then augmented by deep generative neural networks through adversarial learning.  ...  The novelty of the proposed framework focuses on incorporating deep adversarial learning with statistical learning and exploiting learning based data augmentation.  ...  Furthermore, we pre-train and fine-tune deep generative neural networks in adversarial learning scheme for augmenting synthesised intrusion data with high quality. • Extensive experiments on classifying  ... 
arXiv:1901.07949v2 fatcat:jrkvhvbr5nbexksyliwpdcybce

ECG Arrhythmias Detection Using Auxiliary Classifier Generative Adversarial Network and Residual Network

Pu Wang, Borui Hou, Siyu Shao, Ruqiang Yan
2019 IEEE Access  
Data augmentation model is supported by auxiliary classifier generative adversarial network (ACGAN).  ...  INDEX TERMS Electrocardiogram signals, heartbeat arrhythmias detection, auxiliary classifier generative adversarial network, data augmentation, long short-term memory network, residual network. 100910  ...  Generative Adversarial Network (GAN) which was firstly introduced to generate artificial convincing image samples [13] provides a new approach for imbalanced data learning. Madani et al.  ... 
doi:10.1109/access.2019.2930882 fatcat:mijlqmn6xjbu3pcj5cs2ly5724

Towards Fair Cross-Domain Adaptation via Generative Learning [article]

Tongxin Wang, Zhengming Ding, Wei Shao, Haixu Tang, Kun Huang
2020 arXiv   pre-print
Specifically, generative feature augmentation is explored to synthesize effective training data for few-shot source classes, while effective cross-domain alignment aims to adapt knowledge from source to  ...  facilitate the target learning.  ...  Inspired by generative adversarial networks [9] , adversarial-based methods utilize adversarial training to align feature distributions across domains.  ... 
arXiv:2003.02366v2 fatcat:73q2wegggjhixo462wya2czore

Generalization of Deep Neural Networks for Chest Pathology Classification in X-Rays Using Generative Adversarial Networks [article]

Hojjat Salehinejad, Shahrokh Valaee, Tim Dowdell, Errol Colak, Joseph Barfett
2018 arXiv   pre-print
Using chest X-rays as a model medical image, we implement a generative adversarial network (GAN) to create artificial images based upon a modest sized labeled dataset.  ...  Furthermore, we demonstrate that augmenting the original imbalanced dataset with GAN generated images improves performance of chest pathology classification using the proposed DCNN in comparison to the  ...  Generative adversarial networks (GANs) have shown to effectively generate artificial data indiscernible from their real counterparts [8] .  ... 
arXiv:1712.01636v2 fatcat:bnnnbvrvhbgnjegrzc7shq47li

A survey on generative adversarial networks for imbalance problems in computer vision tasks

Vignesh Sampath, Iñaki Maurtua, Juan José Aguilar Martín, Aitor Gutierrez
2021 Journal of Big Data  
It is particularly important that GANs can not only be used to generate synthetic images, but also its fascinating adversarial learning idea showed good potential in restoring balance in imbalanced datasets  ...  The real-world challenges and implementations of synthetic image generation based on GANs are extensively covered in this survey.  ...  Acknowledgements The authors would like to thank the anonymous reviewers for their valuable comments and suggestions on the paper.  ... 
doi:10.1186/s40537-021-00414-0 pmid:33552840 pmcid:PMC7845583 fatcat:g3p6hbjuj5c5vbe23ms4g6ed6q

Dual Autoencoders Generative Adversarial Network for Fraud Detection of Credit Card

Ensen Wu, Hongyan Cui, Roy E. Welsch
2020 IEEE Access  
INDEX TERMS Fraud detection, imbalanced classification, generative adversarial networks, autoencoders.  ...  In this paper, we proposed a Dual Autoencoders Generative Adversarial Network, which can balance the majority and minority classes and learn feature representations of normal and fraudulent transactions  ...  In order to make full use of the information of the samples in the dataset and alleviate the imbalanced-class problem, we proposed Dual Autoencoders Generative Adversarial Network (DAEGAN).  ... 
doi:10.1109/access.2020.2994327 fatcat:okewn2wb7zhzzfynmr3nm2zdkq

Towards Imbalanced Image Classification: A Generative Adversarial Network Ensemble Learning Method

Yangru Huang, Yi Jin, Yidong Li, Zhiping Lin
2020 IEEE Access  
In this paper, we propose a new ensemble framework based on the advanced generative adversarial network and an effective data cleaning way to address the class imbalance problem for weather classification  ...  Experiments show that our approach outperforms the state-of-the-art methods by a huge margin for imbalanced weather classification on several benchmark data sets.  ...  IMBALANCED LEARNING VIA GAN Generative Adversarial Networks (GANs) are powerful generative models which have achieved impressive results in many computer vision tasks such as image generation [21] , super  ... 
doi:10.1109/access.2020.2992683 fatcat:gvjlquuvwzdr5cc3txcmsyx6vi

DATA AUGMENTATION METHOD USING GENERATIVE ADVERSARIAL NETWORKS

Oleksandr Chaikovskyi, Artem Volokyta, Artemi Kyrianov, Heorhii Loutskii
2021 TECHNICAL SCIENCES AND TECHNOLOG IES  
The article discusses a data augmentation method based on generative adversarial networks to improve the accuracy of image classification by convolutional neural networks.  ...  A comparative analysis of the proposed method with classical image augmentation methods was performed.  ...  The possibilities of using generative adversarial networks in the problem of data augmentation remain unconsidered. The research objective.  ... 
doi:10.25140/2411-5363-2021-2(24)-83-91 fatcat:akx6ntin55h2jdyvbuf6fhbopm

Evaluation of Deep Convolutional Generative Adversarial Networks for Data Augmentation of Chest X-ray Images

Sagar Kora Venu, Sridhar Ravula
2020 Future Internet  
Convolutional Generative Adversarial Network (DCGAN).  ...  In this study, we performed data augmentation on the Chest X-ray dataset to generate artificial chest X-ray images of the under-represented class through generative modeling techniques such as the Deep  ...  This study's main contribution is demonstrating the superiority of generative adversarial network based data augmentation. The rest of the paper is structured as follows.  ... 
doi:10.3390/fi13010008 fatcat:bbjubtcubjajxbsghcr4h4ljua
« Previous Showing results 1 — 15 out of 2,770 results