2026· International Journal of Advances in Scientific Research and Engineering· Vol 12, pp. 01-08· 0 citations
TL;DR
An in-depth and up- to-date overview of the GANs environment, principally highlighting the progress made over 2020 and beyond and proposing the idea of hybrid generative systems in the future while emphasizing the oppositional approach's extraordinary and enduring features.
Abstract
Generative Adversarial Networks (GANs) have radically transformed the field of artificial intelligence by offering a highly effective model for understanding complex data distributions and creating new, high-quality content. The evolution of the sector has been incredibly rapid since their invention, resulting in advanced architectural frameworks, highly efficient training techniques, and numerous applications. This review delivers an in-depth and up- to-date overview of the GANs environment, principally highlighting the progress made over 2020 and beyond. We kick off by presenting the basic adversarial concept and the problems that come along with it. Next, through a systematic approach, we depict and discuss the progress of the GANs structures, starting with the superior output of StyleGAN, going through the amalgamation of transformers and 3D data studies, and so on. An enormous part of this paper is invested in presenting a compact, yet extensive, panorama of the most advanced applications found across computer vision, healthcare, data science, and other novel areas. Moreover, we take a deep and critical dive into persistent issues like evaluation, mode collapse, and theoretical understanding, their challenges, and the ways in which recent works have tried to solve them. To wrap up, we consider the onward path of GANs in light of the impressive proliferation of diffusion models and propose the idea of hybrid generative systems in the future while emphasizing the oppositional approach's extraordinary and enduring features.
Generative adversarial networks (GANs) have fundamentally transformed the deep learning field since they enable the creation of synthetic data that closely matches real world data. This paper presents a comprehensive and up‐to‐date review of GANs variants and their revolutionary impact in several domains, and major developments in the new applications. We demonstrate the GANs architecture, versatility of GANs variants such as CycleGAN, bidirectional generative adversarial networks (BiGAN), quantum‐enhanced GAN (Q‐GAN) and StyleGAN. In this work, different GANs variants are analysed and combined with the proposed improvements that enhance stability and performance. Despite their outstanding performance, GANs suffer from instability and mode collapse during training. This paper examines various strategies and improvements to enhance GANs stability and performance, including hybrid architectures that integrate GANs with other deep learning models and practical utility in domain‐specific expert systems. Moreover, in the context of deepfakes, it considers the ethical and legal reflections of GANs generated content. We also contribute to a comprehensive perspective on current applications and future prospects of GANs, underscoring their versatility and promise in areas such as image synthesis, medical imaging, anomaly detection, code synthesis and urban simulation.
Generative Artificial Intelligence (GenAI) has become a foundational paradigm for learning complex data distributions and synthesizing realistic content across text, image, audio, tabular, scientific, and multimodal data. Despite rapid progress, the literature remains fragmented across model families and application domains, making it difficult to compare methodological choices, evaluation practices, and domain-specific deployment constraints. This survey addresses this gap by reviewing GenAI from both an algorithmic and cross-domain perspective. Following a PRISMA-inspired search and screening procedure, we organize representative and technically relevant studies across major GenAI families, including variational autoencoders, generative adversarial networks, diffusion models, autoregressive models, flow-based models, and recent foundation and multimodal models. We synthesize applications across healthcare, agriculture, manufacturing, transportation, earth and environmental systems, computer science and networks, materials science, finance and economics, education, business and services, and creative industries. The review shows that diffusion and autoregressive foundation models increasingly dominate high-fidelity image, language, and multimodal generation, while GANs, VAEs, and flow-based models remain important in data-limited, structured, scientific, and privacy-aware settings. Beyond summarizing applications, the paper compares domain-specific data structures, evaluation practices, robustness concerns, failure modes, and ethical risks. The survey contributes a unified reviewed abstraction of GenAI workflows, a comparison with prior surveys, a domain-aware synthesis of open gaps, and a future roadmap for trustworthy, validated, and responsible GenAI deployment.
A. Javadpour, F. Ja’fari, T. Taleb et al.· IEEE Access· 0 citations
This survey deeply explains the basic principles of representation learning, and introduces its practical application cases in various fields, and points out the main limitations of current models and prospects the future research directions.
Zhiyong Wang, Qiang He, Jun Mou et al.· Expert systems· 0 citations
Adversarial deep learning has emerged as a critical area of research within computer vision, revealing both the vulnerabilities and resilience of modern neural networks. This study provides a comprehensive survey of adversarial attacks and corresponding defense mechanisms, bridging foundational concepts with recent advancements. The taxonomy of adversarial attacks is thoroughly examined, including white-box, limited-information, real-world, and modern attacks, each exploiting specific vulnerabilities in deep learning models. On the defense front, this paper explores an extensive range of strategies, from adversarial training and architectural modifications to certifiable robustness frameworks and semantic-level defenses, emphasizing their strengths and limitations. Despite significant progress, the dynamic and evolving nature of adversarial threats underscores the need for adaptive, human-centered solutions. Integrating robust defenses such as input reconstruction, ensemble-based models, and dynamic mechanisms highlights the field’s innovation, but challenges persist in achieving universal robustness and scalability. This survey emphasizes the importance of interdisciplinary collaboration, blending human perception, computational security, and explainable AI to design defenses that align with real-world complexities and ethical considerations. By critically analyzing current methodologies and proposing future directions, this paper contributes to advancing the security and reliability of computer vision applications. It advocates for a forward-thinking approach that balances technical sophistication with human-centric principles, ensuring that adversarial deep learning evolves into a discipline not just of technical defense, but also of trust, transparency, and accountability.
Maisam Abbas, Ran-Zan Wang· IEEE Open Journal of the Com...· 0 citations
Generative Adversarial Networks (GANs) have become the backbone of data synthesis across multiple domains like healthcare, audio processing, real-time systems, and federated learning. Despite their revolutionary potential, GANs suffer from major challenges in stability, scalability, and data dependence. This seminar presents a critical and comparative review of ten research papers, each offering a unique solution to the core issues of GAN training instability. The reviewed methods encompass domain adaptation, feature distillation, theoretical regularization, adaptive augmentation, and hierarchical federated architectures. This report provides an in-depth literature analysis, followed by a cross-domain metric-wise performance comparison. The results indicate that no single method dominates across all scenarios, but hybrid combinations lead to the best generalizability and stability under constraints like limited data, non IID settings, or real-time computation. Findings are contextualized in terms of practical impact, with implications for the future design of robust, scalable GAN architectures.
C. Murali, R. Anand· International Journal For Mu...· 0 citations
Adversarial examples are purposely crafted to fool Artificial Neural Networks (ANNs) into producing erroneous outputs. Understanding what makes these models vulnerable to such attacks is an open research topic and constitutes a first step toward devising defenses. Focusing on ANNs designed for image classification, we propose a method to analyze these models from an adversarial robustness perspective. The approach is based on the t-distributed Stochastic Neighbor Embedding (t-SNE) technique and allows the visual inspection of the representations learned by an ANN throughout its different layers. Additionally, we propose the Embedding Overlap Robustness RatiO (EORRO) metric to identify potential weak spots in the network by quantifying differences between clean and perturbed images on the t-SNE maps. We validated our approach by studying two ANNs, one designed by humans and another by NeuroEvolution, on CIFAR-10 and CIFAR-100. Our results indicate that differences between clean and perturbed images start to emerge early on in the models, namely in the feature extraction layers of the networks. Guided by the proposed metric, we implemented an ablation and fine-tuning strategy that successfully boosted the robustness of the ANNs against a variant of the Auto-PGD attack under different threat models. More specifically, the post-attack accuracy of the neuroevolved ANN on CIFAR-10 changed from 0% to at least 63.5% in \(L_{2}\) and 27.2% in \(L_{\infty}\) .