FEGAN: A High-Performance Font Enhancement Network for Text CAPTCHA Preprocessing

Machinery fault diagnosis tasks have been well addressed when sufficient and abundant data are available. However, the data imbalance problem widely exists in real-world scenarios, which leads to the performance deterioration of fault diagnosis markedly. To solve this problem, we present a novel imbalanced fault diagnosis method based on the enhanced generative adversarial networks (GAN). By artificially generating fake samples, the proposed method can mitigate the loss caused by the lack of real fault data. Specifically, in order to improve the quality of generated samples, a new discriminator is designed using spectrum normalization (SN) strategy and a two time-scale update rule (TTUR) method is used to stabilize the training process of GAN. Then, an enhanced Wasserstein GAN with gradient penalty is developed to generate high-quality synthetic samples for the fault samples set. Finally, a deep convolutional classifier is constructed to carry out fault classification. The performance and effectiveness of the proposed method are validated on the Case Western Reserve University bearing dataset and rolling bearing dataset acquired from our laboratory. The simulation results show that the proposed method has a superior performance than other methods for imbalanced fault diagnosis tasks.

In general, the imbalanced dataset is a major issue in health applications. The medical data classification faces the imbalanced count of data samples, here at least one class forms only a very small minority of the data, but it is a drawback of most of the machine learning algorithms. The medical datasets are mostly imbalanced in its class labels. When the dataset is imbalanced, the existing classification algorithms typically perform badly on minority class cases. To deal the class imbalance issue, an enhanced generative adversarial network (E-GAN) is proposed in this article. The proposed approach is the consolidation of deep convolutional generative adversarial network and modified convolutional neural network (DCG-MCNN). Initially, the imbalanced data is converted into balanced data in pre-processing process. Data preprocessing comprise of data cleaning, data normalization, data transformation and data reduction using Radius Synthetic minority oversampling technique (RSMOTE) method. The DCG is considered for balancing the dataset generating extra samples under training dataset. This training dataset based, the medical disease classification is enhanced by modified CNN diagnosis model. The proposed system performed is executed in MATLAB. The performance analysis is implemented under the Breast Cancer Wisconsin Dataset that provides the higher maximum geometry mean (MGM) of 8.686, 2.931 and 5.413%, and higher Matthews’s correlation coefficient (MCC) of 9.776, 1.841 and 5.413% compared to the existing methods.

ABSTRACTTo address the challenges posed by incomplete data in passenger flow prediction and organizational tasks, this paper proposes ProbSparse self‐attention conditional generative adversarial imputation net (ProbSA‐CGAIN), a novel imputation model framework built on the enhanced generative adversarial network (GAN). The model leverages conditional GANs for controlled data generation using external conditional information. It adopts a denoising autoencoder structure for reconstructing and estimating missing passenger flow data. The integration of an efficient ProbSparse self‐attention mechanism captures spatiotemporal evolution features, reducing computational complexity. Additionally, the model incorporates auxiliary conditional information to enhance data imputation accuracy by learning interdependencies among multiple data variables. Further, the model integrates local positional encoding and multi‐layer global temporal encoding, offering diverse perspectives on spatiotemporal information. Experimental evaluations with real passenger flow data demonstrate the model's superiority over advanced baseline models across various missing patterns and rates. Notably, it exhibits high stability in data restoration, particularly for datasets with higher missing rates, affirming its effectiveness in predicting and inferring missing passenger flow data based on auxiliary data and multi‐view positional information, ensuring reliable imputation. The experiments also assess the model's proficiency in attributing different spatiotemporal features, confirming its commendable training and restoration efficiency.

Despite several attacks have been proposed, text-based CAPTCHAs are still being widely used as a security mechanism. One of the reasons for the pervasive use of text captchas is that many of the prior attacks are scheme-specific and require a labor-intensive and time-consuming process to construct. This means that a change in the captcha security features like a noisier background can simply invalid an earlier attack. This paper presents a generic, yet effective text captcha solver based on the generative adversarial network. Unlike prior machine-learning-based approaches that need a large volume of manually-labeled real captchas to learn an effective solver, our approach requires significantly fewer real captchas but yields much better performance. This is achieved by first learning a captcha synthesizer to automatically generate synthetic captchas to learn a base solver, and then fine-tuning the base solver on a small set of real captchas using transfer learning. We evaluate our approach by applying it to 33 captcha schemes, including 11 schemes that are currently being used by 32 of the top-50 popular websites including Microsoft, Wikipedia, eBay and Google. Our approach is the most capable attack on text captchas seen to date. It outperforms four state-of-the-art text-captcha solvers by not only delivering a significant higher accuracy on all testing schemes, but also successfully attacking schemes where others have zero chance. We show that our approach is highly efficient as it can solve a captcha within 0.05 second using a desktop GPU. We demonstrate that our attack is generally applicable because it can bypass the advanced security features employed by most modern text captcha schemes. We hope the results of our work can encourage the community to revisit the design and practical use of text captchas.

A series of Generative Adversarial Networks (GANs) could effectively capture the salient features in the dataset in an adversarial way, thereby generating target data. The discriminator of GANs provides significant information to update parameters in the generator and itself. However, the discriminator usually becomes converged before the generator has been well trained. Due to this problem, GANs frequently fail to converge and are led to mode collapse. This situation can cause inadequate learning. In this paper, we apply restart learning in the discriminator of the GAN model, which could bring more meaningful updates for the training process. Based on CIFAR-10 and Align Celeba, the experiment results show that the proposed method could improve the performance of a DCGAN with a low FID score over a stable learning rate scheme. Compared with two other stable GANs—SNGAN and WGAN-GP—the DCGAN with a restart schedule had a satisfying performance. Compared with the Two Time-Scale Update Rule, the restart learning rate is more conducive to the training of DCGAN. The empirical analysis indicates four main parameters have varying degrees of influence on the proposed method and present an appropriate parameter setting.

This paper addresses the task of developing a steganographic method to hide information, resistant to analysis based on the Rich model (which includes several different submodels), using statistical indicators for the distribution of the pairs of coefficients for a discrete cosine transform (DCT) with different values. This type of analysis implies calculating the number of DCT coefficients pairs, whose coordinates in the frequency domain differ by a fixed quantity (the offset). Based on these values, a classifier is trained for a certain large enough data sample, which, based on the distribution of the DCT coefficients pairs for an individual image, determines the presence of additional information in it.A method based on the preliminary container modification before embedding a message has been proposed to mitigate the probability of hidden message detection. The so-called Generative Adversarial Network (GAN), consisting of two related neural networks, generator and discriminator, was used for the modification. The generator creates a modified image based on the original container; the discriminator verifies the degree to which the modified image is close to the preset one and provides feedback for the generator.By using a GAN, based on the original container, such a modified container is generated so that, following the embedding of a known steganographic message, the distribution of DCT coefficients pairs is maximally close to the indicators of the original container.We have simulated the operation of the proposed modification; based on the simulation results, the probabilities have been computed of the proper detection of the hidden information in the container when it was modified and when it was not. The simulation results have shown that the application of the modification based on modern information technologies (such as machine learning and neural networks) could significantly reduce the likelihood of message detection and improve the resistance against a steganographic analysis

Based on data from Badan Siber dan Sandi Negara (BSSN) in 2022, it was reported that a total of 1,950 security vulnerabilities were found in 457 electronic systems across various applications widely used by the public. The purpose of this research is to evaluate the risk of existing security vulnerabilities in the E-Office application and determine the level and impact that these vulnerabilities can cause. This research focuses on information system security, specifically evaluating the risk of security vulnerabilities in the E-Office application of the Ogan Ilir Regency. The research was conducted using the Open Web Application Security Project (OWASP) method with a risk rating assessment. The research process began with a literature review to gather data and information sources, determine the scope and research objectives, test, identify security vulnerabilities, analyze security vulnerabilities, and the results of the analysis. The research subject is the E-Office application of Ogan Ilir Regency, with the object of the research being the security vulnerabilities in that application. OWASPZap was used as a tool to obtain data on security vulnerabilities, and using OWASPZap, 38 security vulnerabilities were found, with 18 of them meeting the criteria of the OWASP Top 10. Our findings indicate that the security vulnerabilities in the E-Office application of Ogan Ilir Regency include vulnerabilities in authentication levels, access control, configuration, and data validation processes.

Enhanced generative adversarial network for extremely imbalanced fault diagnosis of rotating machine

Joint image-to-image translation with denoising using enhanced generative adversarial networks

When deciding on a kidney tumor’s diagnosis and treatment, it is critical to take its morphometry into account. It is challenging to undertake a quantitative analysis of the association between kidney tumor morphology and clinical outcomes due to a paucity of data and the need for the time-consuming manual measurement of imaging variables. To address this issue, an autonomous kidney segmentation technique, namely SegTGAN, is proposed in this paper, which is based on a conventional generative adversarial network model. Its core framework includes a discriminator network with multi-scale feature extraction and a fully convolutional generator network made up of densely linked blocks. For qualitative and quantitative comparisons with the SegTGAN technique, the widely used and related medical image segmentation networks U-Net, FCN, and SegAN are used. The experimental results show that the Dice similarity coefficient (DSC), volumetric overlap error (VOE), accuracy (ACC), and average surface distance (ASD) of SegTGAN on the Kits19 dataset reach 92.28%, 16.17%, 97.28%, and 0.61 mm, respectively. SegTGAN outscores all the other neural networks, which indicates that our proposed model has the potential to improve the accuracy of CT-based kidney segmentation.

Real data with privacy and confidentiality concerns are not often available or are too expensive to afford in respect of both time and money. In this situation, it is a good alternative to use synthetic data. The objective of this research is to generate realistic synthetic data so that people can use it freely. We propose a synthetic data generation model based on boundary-seeking generative adversarial networks (BGANs)–designated as medical BGAN or medBGAN and compare its performances with an existing method medical GAN (medGAN). We aim to perform the investigation on several datasets in two different domains: electronic health records (EHRs) in the medical domain and a crime dataset in the City of Los Angeles Police Department. Firstly, we train the models and generate synthetic data by using these trained models. We then analyze and compare the models' performance by applying some statistical methods (dimension-wise average and Kolmogorov-Smirnov test) and two machine learning tasks (association rule mining and prediction). The comprehensive analysis of this study shows that the proposed model is more efficient in generating realistic synthetic data than those generated using medGAN.

Super-Resolution (SR) techniques for image restoration have recently been gaining attention due to their excellent performance. For powerful learning abilities, Generative Adversarial Networks (GANs) have been proven to have achieved great success. In this paper, we propose an Enhanced Generative Adversarial Network (EGAN) for improving its effects for a real-time Super-Resolution task. The main content of this paper are as follows: (1) We adopted the Laplacian pyramid framework as a pre-trained module, which is beneficial for providing multiscale features for our input. (2) At each feature block, a convolutional skip-connections network, which may contain some latent information, was significant for the generative model to reconstruct a plausible-looking image. (3) Considering that the edge details usually play an important role in image generation, a perceptual loss function was defined to train and seek the optimal parameters. Quantitative and qualitative evaluations were demonstrated so that our algorithm not only took full advantage of the Convolutional Neural Networks (CNNs) to improve the image quality, but also performed better than other algorithms in speed and performance for real-time Super-Resolution tasks.

Synthetic augmentation for semantic segmentation of class imbalanced biomedical images: A data pair generative adversarial network approach

In the past decade, several applications have emerged in predicting children’s images using their parents via Generative Adversarial Networks (GANs). However, no one has tackled the problem of predicting one of the parents using the other parent and their children or answering the question of the possibility of deducing the parent images from the children and other parent image features. It could be used in parental identification cases. Moreover, it could help children who don’t know one of their parents to have a visual representation of their images. To perform this task, several obstacles were overcome, like the small number of parent pairs in the dataset and stabilizing the GANs to produce good-looking images. The proposed method depends on dual GAN architecture in addition to adaptive instance normalization layers and introducing a triple loss function to stabilize further and improve the resulting images. The results were proven using a kinship verification model, a face verification model, and other well-known evaluation metrics, which showed that the generated parent images are of decent quality compared to real parents’ images with affordable computational hardware. As a result, a novel method is developed that could produce unknown parent images.

Exploring adversarial deep learning for fusion in multi-color channel skin detection applications