Generative Adversarial Networks (GANs) in Cybersecurity

Computer vision is one of the hottest research fields in deep learning. The emergence of generative adversarial networks (GANs) provides a new method and model for computer vision. The idea of GANs using the game training method is superior to traditional machine learning algorithms in terms of feature learning and image generation. GANs are widely used not only in image generation and style transfer but also in the text, voice, video processing, and other fields. However, there are still some problems with GANs, such as model collapse and uncontrollable training. This paper deeply reviews the theoretical basis of GANs and surveys some recently developed GAN models, in comparison with traditional GAN models. The applications of GANs in computer vision include data enhancement, domain transfer, high-quality sample generation, and image restoration. The latest research progress of GANs in artificial intelligence (AI) based security attack and defense is introduced. The future development of GANs in computer vision is also discussed at the end of the paper with possible applications of AI in computer vision.

Bangla handwritten character recognition is known to be one of the most classical problem in the field of machine learning. In order to solve a machine learning problem one must thing is dataset. The more varied data a model sees the better it learns. Generative adversarial networks (GANs) are a group of neural networks that are used in unsupervised machine learning. It helps to resolve many difficult operations such as image generation from description, transforming low resolution image into high resolution, retrieving image contents given a small pattern etc. GAN's have many other promising applications in machine learning. There are many variations available for GAN. One of the variation of GAN is Conditional Generative Adversarial Networks(cGAN). This kind of GAN is used for generating a specific type of image. In this work we have used cGAN for generating Class Based Character Generation. This work can help researchers to generate handwritten characters to enhance the perfomance of deep learning models. We have trained this model to generate 50 Basic Bangla Characters, 10 Bangla Numerals and 24 Compound characters.

This study investigates the scientific development of Artificial Intelligence (AI) and Machine Learning (ML) applications in Human Resource Management (HRM) through bibliometric analysis. To this end, 522 academic publications indexed in the Scopus database between 2020 and 2024 were analyzed using the R-based bibliometrix package and VOSviewer software. Descriptive analysis, scientific productivity metrics, and content analysis techniques were employed. The findings revealed three main patterns. First, research on AI and ML applications in HRM has grown significantly—particularly between 2022 and 2024—driven by post-pandemic digital transformation. Second, India, China, and the USA lead in research output, while the UK and France demonstrate strong citation impact, indicating a globally expanding research ecosystem. Third, the thematic focus of research is shifting from technical infrastructure toward more human-centered and ethical dimensions. Additionally, keyword co-occurrence network analysis identified three major thematic clusters: HRM functions, AI applications, and machine learning analytics, highlighting the field’s interdisciplinary nature. Compared to the previous studies, this research provides a more comprehensive bibliometric analysis of AI and ML applications in HRM. It is the first extensive study to map the intellectual evolution of the field from a multidisciplinary perspective. Furthermore, it charts research trends and collaboration networks, revealing a shift from technical implementations to strategic integration. In conclusion, this analysis offers new insights to the literature by illustrating the technological evolution in HRM and highlighting the growing significance of cutting-edge approaches such as AI and ML, reaffirming the field as a timely and impactful area of research.

Generative Adversarial Networks (GANs) have become a pivotal advancement in machine learning and artificial intelligence, enabling the generation of highly realistic data. This paper provides a comprehensive overview of GANs, focusing on their foundational principles, various techniques, and diverse applications. Emphasis is placed on the transformative impact of GANs in image generation and data augmentation. The proposed method demonstrates significant performance improvements, achieving an accuracy of 95.3%. Furthermore, the method shows a mean absolute error (MAE) of 0.501 and a root mean square error (RMSE) of 0.109, highlighting its effectiveness in producing high-quality synthetic data. Challenges associated with GANs, such as mode collapse and training instability, are also addressed, along with innovations introduced to mitigate these issues. This paper aims to elucidate the mechanisms behind GANs, explore their applications, and outline future research directions in this dynamic field.

From real–time tumor classification to operative outcome prediction, applications of machine learning to neurosurgery are powerful. However, the translation of many of these applications are restricted by the lack of “big data” in neurosurgery. Important restrictions in patient privacy and sharing of imaging data reduce the diversity of the datasets used to train resulting models and therefore limit generalizability. Synthetic learning is a recent development in machine learning that generates synthetic data from real data and uses the synthetic data to train downstream models while preserving patient privacy. Such an approach has yet to be successfully demonstrated in the spine surgery domain. Spine radiographs were collected from the VinDR–SpineXR dataset, with 1470 labeled as abnormal and 2303 labeled as normal. A conditional generative adversarial network (GAN) was trained on the radiographs to generate a spine radiograph and normal/abnormal label. A modified conditional GAN (SpineGAN) was trained on the same task. A convolutional neural network (CNN) was trained using the real data to label abnormal radiographs. A CNN was trained to label abnormal radiographs using synthetic images from the GAN and in a separate experiment from SpineGAN. Using the real radiographs, an AUC of 0.856 was achieved in abnormality classification. Training on synthetic data generated by the standard GAN (AUC of 0.814) and synthetic data generated by our SpineGAN (AUC of 0.830) resulted in similar classifier performance. SpineGAN generated images with higher FID and lower precision scores, but with higher recall and increased performance when used for synthetic learning. The successful application of synthetic learning was demonstrated in the spine surgery domain for the classification of spine radiographs as abnormal or normal. A modified domain–relevant GAN is introduced for the generation of spine images, evidencing the importance of domain–relevant generation techniques in synthetic learning. Synthetic learning can allow neurosurgery to use larger and more diverse patient imaging sets to train more generalizable algorithms with greater patient privacy.

Thyroid dysfunction is one of the most common endocrine diseases. About 4.7% of the United States population has undiagnosed thyroid disease (Garmendia Madariaga, Santos Palacios, Guillén-Grima, & Galofré, 2014). Thyroid nodules could be present in up to 67% of the population (Ezzat, Sarti, Cain, & Braunstein, 1994). Increased incidence of thyroid nodules has been attributed to increased use of imaging modalities and improvement in imaging technology (Singh, Singh, & Khanna, 2012). Technological improvements in ultrasound including elastography, 3D ultrasound (Liang et al., 2019) 274and quantitative ultrasound (Goundan et al., 2019) have been used to improve the diagnostic accuracy. Computer-aided diagnosis software that can automatically detect different features in the thyroid nodules and generate a report has been cleared by the FDA (Lu, Shi, Zhao, Song, & Li, 2019). Similarly, artificial intelligence (AI) algorithms have been used in the diagnosis and management of thyroid diseases. One of the first papers using AI in the diagnosis of thyroid disease was by Sharpe et al. in 1993. They used a multilayer perceptron trained by back-propagation and a learning vector quantization network to investigate the robustness of these models on noisy diagnostic data. In recent years, most of the AI research in thyroidology has been focused on the diagnosis and management of thyroid nodules. Initial approaches used texture analysis to classify thyroid ultrasound images. Later, AI techniques such as machine learning (ML) and an advanced form of ML, deep learning (DL) algorithms were used. In this chapter, we discuss the use of AI in thyroid imaging, cytopathological diagnosis of thyroid nodules and molecular markers. The use of wearable devices and generative adversarial networks in thyroidology is also discussed in this chapter.

The gas chromatography analysis method for chemical substances enables accurate analysis to precisely distinguish the components of a mixture. This paper presents a technique for augmenting time-series data of chemicals measured by gas chromatography instruments with artificial intelligence techniques such as generative adversarial networks (GAN). We propose a novel GAN algorithm called GCGAN for gas chromatography data, a unified model of autoencoder (AE) and GAN for effective time-series data learning with an attention mechanism. The proposed GCGAN utilizes AE to learn a limited number of data more effectively. We also build a layer of high-performance generative adversarial neural networks based on the analysis of the features of data measured by gas chromatography instruments. Then, based on the proposed learning, we synthesize the features embedded in the gas chromatography data into a feature distribution that extracts the temporal variability. GCGAN synthesizes the features embedded in the gas chromatography data into a feature distribution that extracts the temporal variability of the data over time. We have fully implemented the proposed GCGAN and experimentally verified that the data augmented by the GCGAN have the characteristic properties of the original gas chromatography data. The augmented data demonstrate high quality with the Pearson correlation coefficient, Spearman correlation coefficient, and cosine similarity all exceeding 0.9, significantly enhancing the performance of AI classification models by 40%. This research can be effectively applied to various small dataset domains other than gas chromatography data, where data samples are limited and difficult to obtain.

The amount of structural damage image data produced in the aftermath of an earthquake can be staggering. It is challenging for a few human volunteers to efficiently filter and tag these images with meaningful damage information. There are several solution to automate post-earthquake reconnaissance image tagging using Machine Learning (ML) solutions to classify each occurrence of damage per building material and structural member type. ML algorithms are data driven; improving with increased training data. Thanks to the vast amount of data available and advances in computer architectures, ML and in particular Deep Learning (DL) has become one of the most popular image classification algorithms producing results comparable to and in some cases superior to human experts. These kind of algorithms need the input images used for the training to be labeled, and even if there is a large amount of images most of them are not labeled and it takes structural engineers a large amount of time to do it. The current data earthquakes image data bases do not contain the label information or is incomplete slowing significantly the advance of a solution and are incredible difficult to search. To be able to train a ML algorithm to classify one of the structural damages it took the architecture school an entire year to gather 200 images of the specific damage. That number is clearly not enough to avoid overfitting so for this thesis we decided to generate synthetic images for the specific structural damage. In particular we attempt to use Generative Adversarial Neural Networks (GANs) to generate the synthetic images and enable the fast classification of rail and road damage caused by earthquakes. Fast classification of rail and road damage can allow for the safety of people and to better prepare the reconnaissance teams that manage recovery tasks. GANs combine classification neural networks with generative neural networks. For this thesis we will be combining a convolutional neural network (CNN) with a generative neural network. By taking a classifier trained in a GAN and modifying it to classify other images the classifier can take advantage of the GAN training without having to find more training data. The classifier trained in this way was able to achieve an 88\% accuracy score when classifying images of structural damage caused by earthquakes.

Artificial intelligence for patient scheduling in the real-world health care setting: A metanarrative review

In recent years, deep neural networks have demonstrated high efficiency in solving the problems associated with image processing and analysis. The latest studies in generative adversarial neural networks open up broad prospects for solving problems in image style transfer, cross-domain adaptation, and the generation of new data for a target probability distribution. The ability of generative networks to implement complex and weakly formalized transformations allows the information systems based on generative adversarial technologies to solve problems in machine learning in a manner similar to human creative thinking. This paper presents the results of an experimental study on the design, training and deployment of an intelligent control system for a CNC laser engraver based on the generative adversarial network. In order to train deep models, large amounts of data are required. Therefore, one of the main challenges in this experimental study is a lack of labelled training dataset. The proposed control system for the laser engraver based on the deep generative model allows decreasing the time of the manufacturing process.

Purpose: To develop an artificial intelligence based generative design framework to optimize radiation shielding for satellites and spacecraft using a genetic algorithm combined with a generative adversarial network and compare the performance to using only a genetic algorithm. Methods: The optimization framework is developed and tested on three different models, a simple cube, the SpaceX Dragon vehicle, and the STPSat-4 satellite. Each model's geometry is created in our Monte Carlo particle transport code with an added allowed shielding volume. Each model is exposed to a simulated radiation source using the Monte Carlo code. We use a genetic algorithm, GA, where the material distribution is represented by individuals in the algorithm. GAs are evolutionary algorithms primarily used to perform optimizations. The goal of the optimization is to minimize the dose to a specified volume inside the vehicle. Halfway through the optimization, the results are used to train a generative adversarial network, GAN, which is a type of generative model based on adversarial training. The GAN then produces new shielding solutions that are fed into the optimization process. The shielding solutions produced by the GAN-assisted-GA are compared to those produced by the GA only, and both are compared to the reference baseline of aluminum shielding. Results: Our optimization framework was able to reduce the internal dose by up to 20% for the generic satellite, 14% for the Dragon vehicle, and up to 45% for the STPSat-4 for equal weights of uniform aluminum. We found the GAN-assisted-GA was able to improve the overall optimization performance by 6% for the simple cube and 8% for the Dragon vehicle. Conclusions: Our genetic algorithm based optimization framework was able to produce radiation shielding profiles with reduced dose compared to aluminum references of the same weight. We also showed increased performance by incorporating a generative adversarial network into the genetic algorithm optimization process. This work demonstrates the ability of our approach to be used to design radiation shielding for spacecraft and satellites.

We study two important concepts in adversarial deep learning---adversarial training and generative adversarial network (GAN). Adversarial training is the technique used to improve the robustness of discriminator by combining adversarial attacker and discriminator in the training phase. GAN is commonly used for image generation by jointly optimizing discriminator and generator. We show these two concepts are indeed closely related and can be used to strengthen each other---adding a generator to the adversarial training procedure can improve the robustness of discriminators, and adding an adversarial attack to GAN training can improve the convergence speed and lead to better generators. Combining these two insights, we develop a framework called Rob-GAN to jointly optimize generator and discriminator in the presence of adversarial attacks---the generator generates fake images to fool discriminator; the adversarial attacker perturbs real images to fool the discriminator, and the discriminator wants to minimize loss under fake and adversarial images. Through this end-to-end training procedure, we are able to simultaneously improve the convergence speed of GAN training, the quality of synthetic images, and the robustness of discriminator under strong adversarial attacks. Experimental results demonstrate that the obtained classifier is more robust than the state-of-the-art adversarial training approach, and the generator outperforms SN-GAN on ImageNet-143.

Three-dimensional microstructure reconstruction is indispensable for understanding the performance and reliability of SOFC electrodes. Not only the microstructure parameters, but also SOFC electrochemical characteristics such as overpotentials can be calculated when combined with numerical simulations. The most common method to analyze 3-D structures with a feature size of 0.01 – 10 μm is a focused ion beam - scanning electron microscope (FIB-SEM). However, there’s a tradeoff between reconstruction volume size and resolution. Besides, in order to obtain high quality reconstruction, accumulation of know-hows for pre and post-processing is required. Therefore, fast screening of the microstructures is not easy for FIB-SEM due to the difficulty of measurement. On the other hand, a single SEM image can be obtained very easily. An arising question is if it is possible to extract properties of microstructures and numerically synthesize 3-D model directly from a single 2-D SEM image.In recent years, machine learning techniques have become a powerful tool for image processing. Nevertheless, applications of machine learning in the field of porous materials, in particular fuel cells and batteries are still limited. The previous works concentrated on relatively simple artificial neural networks (ANN), but the class of neural networks that can effectively analyze visual images is the convolutional neural network (CNN). Gayon-Lombardo et al. (1) demonstrated a successful application of generative adversarial network (GAN) based on CNN layers to fabricate synthetic 3-D SOFC microstructures. It is indicated that the GAN-based approach can be very effective, but the algorithm requires 3-D teaching data (GAN3Dto3D).In the scope of this research, a novel method for fabrication of synthetic 3-D microstructure directly from a 2-D SEM image is proposed (Fig. 1A). The GAN2Dto3D network consists of a 3-D microstructure generator and a discriminator which operate on 2-D data. Each microstructure fabricated by the generator is treated as a set of individual cross-sectional 2-D images. The discriminator checks the validity of each 2-D slice in the generated microstructure in all spatial directions (height, width and thickness). Patches extracted from a real 2-D cross-section image are used as training data. In each training iteration, new random patches are extracted to increase the number of available training data. Additionally, the training images are augmented by random horizontal and vertical flipping. As all of the cross-section of the newly generated microstructure has to be statistically equivalent to the real 2-D cross-section, the generated 3-D microstructure is smooth in all spatial directions.The GAN2Dto3D approach is tested on the dataset of real SOFC microstructures. For the real microstructure, a set of nickel (Ni) – gadolinium doped ceria (GDC) microstructures was fabricated. All composite anode samples were prepared with NiO (AGC Seimi, Japan) and GDC (Gd0.1Ce0.9O ShinEtsu, Japan) powders mixed in a designated proportion and sintered at 1350 oC. Differences in the structure are due to the initial anode slurry composition and packing density. The solid phase fractions were controlled by GDC share in the composite in the range of 30 – 70 vol.%, and their porosity was controlled by isostatic pressing (2). 3-D microstructures were reconstructed by FIB-SEM and used as the ground truth data for the validation of GAN2Dto3D model. The results of the GAN2Dto3D algorithm applied to generate two synthetic microstructures with different GDC share and the porosity are shown in Fig. 1B and 1C. The size of the generated microstructures is 64 × 64 × 64 voxels, which is equivalent to 6.4 × 6.4 × 6.4 µm. The real microstructures reconstructed with FIB-SEM are shown for comparison. The proposed GAN algorithm produces realistic microstructures, which indicates that GAN has a great potential to enable fast evaluation of various samples without carrying out complex FIB-SEM measurements.1. Gayon-Lombardo, L. Mosser, N. P. Brandon, and S. J. Cooper, npj Comput. Mater., 6, 1–11 (2020).2. Komatsu, A. Sciazko, and N. Shikazono, J. Power Sources, 485, 229317 (2021). Figure 1

Application of machine learning in carbon capture and storage: An in-depth insight from the perspective of geoscience

Machine Learning (ML) has proven to be effective in many application domains. However, ML methods can be vulnerable to adversarial attacks, in which an attacker tries to fool the classification/prediction mechanism by crafting the input data. In the case of ML-based Network Intrusion Detection Systems (NIDSs), the attacker might use their knowledge of the intrusion detection logic to generate malicious traffic that remains undetected. One way to solve this issue is to adopt adversarial training, in which the training set is augmented with adversarial traffic samples. This paper presents an adversarial training approach called GADoT, which leverages a Generative Adversarial Network (GAN) to generate adversarial DDoS samples for training. We show that a state-of-the-art NIDS with high accuracy on popular datasets can experience more than 60% undetected malicious flows under adversarial attacks. We then demonstrate how this score drops to 1.8% or less after adversarial training using GADoT.