Privacy Preserving Data Analysis With Generative AI

The general objective of the research is to determine the advances related to Generative Artificial Intelligence. Methodology, in this research, 47 documents have been selected, carried out in the period 2014 - 2023; including: scientific articles, review articles and information from websites of recognized organizations. Results, Generative Artificial Intelligence is demonstrating its importance in various human activities, making it necessary to use it ethically and responsibly. Conclusions, the general objective of the research is to determine the advances related to Generative Artificial Intelligence. Artificial intelligence has evolved from predictive to generative. Key Techniques: Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), Autoregressive Models. Countries are establishing standards for the ethical use of AI, while respecting human rights. Currently, AI has many applications in human activity, but the ethical use of AI is necessary. Various countries are establishing regulations in this regard. Generative Artificial Intelligence is demonstrating its importance in various human activities, making it necessary to use it ethically and responsibly. The specific objectives of the research are to identify the applications and the software of Generative Artificial Intelligence. Applications: Generating realistic images, creating natural language text, composing music. Generative artificial intelligence (AI) tools, such as Bard, ChatGPT, and GitHub CoPilot.

Federated learning (FL), as a distributed learning mechanism, can have model training completed without directly uploading original data, effectively reducing the risk of privacy leakage. However, through the shared gradient information, research shows that adversaries may reconstruct the original data. To further protect the privacy of federated learning, a federated learning defense scheme is proposed based on generative adversarial networks (GAN), which is combined with adaptive differential privacy. Firstly, the real data distribution features are learned through GAN, and replaceable pseudo data are generated. Then, the pseudo data are added with adaptive noise. Finally, the pseudo gradient generated by the pseudo data in the model is used to replace the real gradient so that adversaries cannot obtain the real gradient to further protect the privacy of user data. After simulation experiments are carried out on the MNIST dataset, the algorithm is verified using the gradient attack method. The experimental results show that the proposed algorithm is superior to the federated learning algorithm based on differential privacy in accuracy. Compared with the FedAvg algorithm, only 0.48% accuracy is lost. Therefore, it achieves a good balance between algorithm accuracy and data privacy.

Generative artificial intelligence (GAI), a specialized branch of artificial intelligence, has developed as a dynamic discipline that drives innovation and creativity across several domains. It is concerned with creating models that can autonomously produce novel text, images, videos, music, 3D, code, and more. GAI is distinguished by its capacity to acquire knowledge from extensive datasets, identify recurring patterns, capture distributions, and produce novel content demonstrating similar features. This review presents a comprehensive historical overview of the development and progression of GAI techniques over the years. Various essential methodologies employed in developing GAI are also discussed, including Generative Adversarial Networks (GANs), Variational AutoEncoders (VAEs), transformers, and diffusion models. Moreover, a detailed overview of the technologies used in GAI is provided for generating images, videos, music, code, and text, such as ChatGPT, DALL-E, Midjourney, Claude, Bard, GitHub Copilot, and others. The research subsequently introduces the different datasets used to train the GAI models and the evaluation metrics for evaluating their performances. Ultimately, the research investigates the diverse applications of GAI across various domains, challenges, and ethical implications.

Purpose: This paper investigates the integration of multimodal generative artificial intelligence (GenAI) frameworks for enhancing image captioning and document classification, focusingparticularly on applications in healthcare. De-sign/Methodology/Approach: A systematic analysis of state-of-the-art architectures Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and Transformer-based models is conducted. We evaluate their capacity to process heterogeneous data (text and images), with experiments carried out on benchmark datasets including Reuters-21578, 20 Newsgroups, MS-COCO, Flickr30k, FUNSD, CORD, and healthcare datasets such as chest X-rays. Findings: Experimental results indicate that CNN and Hierarchical Attention Networks achieve high document classification accu-racy (>92%), while transformer-based captioning systems outperform traditional models with BLEU (35%), METEOR (28%), CIDEr (105%), and SPICE (22%). Instruction-tuned Vision-Language Models (VLMs) such as InstructBLIP and LLa-VA-1.5 further enhance zero-shot captioning and multimodal reasoning. In healthcare applications, multimodal integration improves diagnostic imaging interpretation, clinical note classification, and automated report generation. Practical Implica-tions: The framework demonstrates potential in domains requiring context-rich outputs, including medical imaging, pa-tient data analysis, and cross-domain information retrieval. Originality/Value: Unlike previous studies, this work offers a consolidated evaluation of multimodal generative AI through comparative experimentation, integration of recent models (OCR-free document AI, RAG, SAM-based grounding), and ethical considerations, establishing a roadmap for future re-search.

Recent advancements in generative artificial intelligence (AI) have introduced novel opportunities for the application of AI within the financial sector. This chapter examines the various ways in which generative AI is contributing to the rapidly evolving landscape of finance. While traditional machine learning techniques have long been applied to financial tasks such as customer service, text summarization, risk prediction, algorithmic trading, and document processing, generative AI offers enhanced capabilities aimed at improving operational efficiency, elevating customer experience, and enabling responsible growth. Applications of generative AI in finance now extend to areas including decision-making, risk assessment, portfolio optimization, personalized financial advising, fraud detection, and predictive analytics. The field encompasses a diverse set of models, including generative adversarial networks (GANs), variational autoencoders (VAEs), temporal point processes (TPPs), transformers, and large language models (LLMs). This chapter explores how these models are applied in financial contexts, highlighting both theoretical foundations and practical implementations. A dedicated case study is presented, summarizing recent literature on the use of LLMs in financial tasks, including approaches such as zero-shot and few-shot learning with pretrained models, domain-specific fine-tuning, and training models from the ground up. Finally, the chapter discusses key opportunities and challenges associated with generative AI in FinTech, including the balance between innovation and responsibility, and the need for enhanced interpretability, robustness, and ethical compliance in financial applications, hence aiding towards goals of Industry 5.0.

<span lang="EN-US">Edge artificial intelligence (Edge AI) involves the implementation of AI algorithms and models directly on local edge devices, such as sensors or internet of things (IoT) devices. This allows for immediate processing and analysis of data without the need for continuous dependence on cloud infrastructure. Concerns about privacy have grown importance in recent years for businesses looking to uphold end-user expectations and safeguard business models. Federated learning (FL) has emerged as a novel approach to enhance privacy. To improve generalization qualities, FL trains local models on local data. These models then collaborate to update a global model. Each edge device (like smartphones, IoT sensors, or autonomous vehicles) trains a local model on its own data. This local training helps in capturing data patterns specific to each device or node. Poisoning, backdoors, and generative adversarial network (GAN)-based attacks are currently the main security risk. Nevertheless, the biggest threat to FL’s privacy is from inference-based assaults such as model inversion attacks, differential privacy shortcomings and FL utilizes blockchain and cryptography technologies to improve privacy on edge devices. This paper presents a thorough examination of the current literature on this subject. <br /> In more detail, we study the background of FL and its different existing applications, types, privacy threats and its techniques for privacy preservation.</span>

Data analysis is expected to provide accurate descriptions of the data. However, this is in opposition to privacy requirements when working with sensitive data. In this case, there is a need to ensure that no disclosure of sensitive information takes place by releasing the data analysis results. Therefore, privacy-preserving data analysis has become significant. Enforcing strict privacy guarantees can significantly distort data or the results of the data analysis, thus limiting their analytical utility (i.e., differential privacy). In an attempt to address this issue, in this paper we discuss how “integral privacy”; a re-sampling based privacy model; can be used to compute descriptive statistics of a given dataset with high utility. In integral privacy, privacy is achieved through the notion of stability, which leads to release of the least susceptible data analysis result towards the changes in the input dataset. Here, stability is explained by the relative frequency of different generators (re-samples of data) that lead to the same data analysis results. In this work, we compare the results of integrally private statistics with respect to different theoretical data distributions and real world data with differing parameters. Moreover, the results are compared with statistics obtained through differential privacy. Finally, through empirical analysis, it is shown that the integral privacy based approach has high utility and robustness compared to differential privacy. Due to the computational complexity of the method we propose that integral privacy to be more suitable towards small datasets where differential privacy performs poorly. However, adopting an efficient re-sampling mechanism can further improve the computational efficiency in terms of integral privacy.

This article presents a comprehensive survey on the integration of Generative Artificial Intelligence (AI) technologies in radar applications, with a focus on enhancing radar data processing and system capabilities. Generative AI techniques, particularly Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), are explored for their potential to address persistent challenges in radar technology such as noise management, data augmentation, and target classification. The study investigates how GANs can generate synthetic radar datasets, aiding in model training when actual data is scarce, and how VAEs contribute to signal processing by denoising and reconstructing accurate radar signals. The analysis includes case studies on clutter suppression, radar data augmentation, beam blockage correction, and data fusion, highlighting the transformative impact of Generative AI on radar systems. This paper aims to provide insights into the current advancements and future directions of Generative AI applications in radar, suggesting that these technologies hold significant promise for improving the accuracy and efficiency of radar systems in diverse and dynamic environments.

In recent years, the manufacturing industry has undergone transformative changes spurred by the rapid evolution of artificial intelligence (AI), particularly Generative AI (GenAI). As a subset of AI capable of creating new data from learned patterns, GenAI is poised to reshape manufacturing processes by enhancing productivity, product customization, quality assurance, and operational efficiency. This review synthesizes key findings from scholarly articles published in the first half of 2024, with a primary focus on three GenAI models: Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and Transformer-Based Architectures. The paper critically analyzes the roles and capabilities of GenAI technologies in improving predictive maintenance, supply chain optimization, and sustainable production. It also sheds light on the prevailing challenges and potential future advancements of GenAI integration in industrial environments.

With the continuous development of vehicular ad hoc networks (VANET) security, using federated learning (FL) to deploy intrusion detection models in VANET has attracted considerable attention. Compared to conventional centralized learning, FL retains local training private data, thus protecting privacy. However, sensitive information about the training data can still be inferred from the shared model parameters in FL. Differential privacy (DP) is sophisticated technique to mitigate such attacks. A key challenge of implementing DP in FL is that non-selectively adding DP noise can adversely affect model accuracy, while having many perturbed parameters also increases privacy budget consumption and communication costs for detection models. To address this challenge, we propose FFIDS, a FL algorithm integrating model parameter pruning with differential privacy. It employs a parameter pruning technique based on the Fisher Information Matrix to reduce the privacy budget consumption per iteration while ensuring no accuracy loss. Specifically, FFIDS evaluates parameter importance and prunes unimportant parameters to generate compact sub-models, while recording the positions of parameters in each sub-model. This not only reduces model size to lower communication costs, but also maintains accuracy stability. DP noise is then added to the sub-models. By not perturbing unimportant parameters, more budget can be reserved to retain important parameters for more iterations. Finally, the server can promptly recover the sub-models using the parameter position information and complete aggregation. Extensive experiments on two public datasets and two F2MD simulation datasets have validated the utility and superior performance of the FFIDS algorithm.

Generative artificial intelligence, especially with regard to the generative adversarial network (GAN), is an important research area in radiology as evidenced by a number of literature reviews on the role of GAN in radiology published in the last few years. However, no review article about GAN in pediatric radiology has been published yet. The purpose of this paper is to systematically review applications of GAN in pediatric radiology, their performances, and methods for their performance evaluation. Electronic databases were used for a literature search on 6 April 2023. Thirty-seven papers met the selection criteria and were included. This review reveals that the GAN can be applied to magnetic resonance imaging, X-ray, computed tomography, ultrasound and positron emission tomography for image translation, segmentation, reconstruction, quality assessment, synthesis and data augmentation, and disease diagnosis. About 80% of the included studies compared their GAN model performances with those of other approaches and indicated that their GAN models outperformed the others by 0.1–158.6%. However, these study findings should be used with caution because of a number of methodological weaknesses. For future GAN studies, more robust methods will be essential for addressing these issues. Otherwise, this would affect the clinical adoption of the GAN-based applications in pediatric radiology and the potential advantages of GAN could not be realized widely.

Among the broad area of artificial intelligence (AI), generative AI algorithms have emerged as a revolutionary technology able to produce highly realistic ‘synthetic’ data, akin to standard simulation but with fewer contraints. The main focus of generative AI has been on phenotypes, but here we argue it can serve as well for generating synthetic environments and genotypes. This data-driven technology may be able to overcome some of the limitations that standard simulations have, such as strong assumptions on the underlying genotype to phenotype map. We discuss key features of popular generative models including autoregressive models, generative adversarial networks, variational autoencoders, diffusion and flow-based models. Several of these methods utilize a latent space, often of lower dimensionality than the raw data, that can help making the models interpretable and can be a link between simulation and generative algorithms. Augmenting data as realistically as possible with genAI can improve inference and predictive performance of genomic prediction models, but symbolic simulation will continue to play a fundamental role in predictive breeding. A hybrid tool that implements both approaches can be extremely powerful to evaluate predictive breeding strategies in silico. One promising direction is to simulate novel genotypes using conventional methods, then apply generative models to produce realistic phenotypes conditional on genotype and environment.

The semiconductor industry plays a vital role in driving technological advancements, and the incorporation of AI (Artificial Intelligence) can greatly enhance its efficiency and productivity. Through optimizing material usage and reducing defects, AI can significantly reduce costs and enhance production efficiency and product quality. However, despite the increasing interest in AI applications in the semiconductor industry, comprehensive reviews are lacking to systematically analyze existing research and identify the challenges and opportunities in this field. This review aims to bridge this gap by providing a thorough overview of AI-driven techniques in optimizing semiconductor manufacturing and offering valuable insights for future research directions. The integration of Artificial Intelligence (AI) into chip design marks a transformative phase for the semiconductor industry. Traditional design methodologies, often labor-intensive and time-consuming, are increasingly constrained by human expertise and iterative processes. Generative AI, utilizing advanced machine learning models such as Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs), offers innovative approaches to automate and optimize various stages of chip design. This paper examines how generative AI can revolutionize chip design by automating complex tasks, including architecture exploration, circuit optimization, and layout generation. Through case studies, we demonstrate significant improvements in design efficiency, performance optimization, and reduced time-to-market. Additionally, we address challenges such as data availability, model interpretability, and the integration of AI-generated designs into existing verification workflows. The findings highlight the potential of generative AI to enhance design capabilities, reduce development costs, and accelerate innovation in semiconductor technology.

Edge servers and mobile devices are often assigned a large number of computing tasks. However, the data involved in computing tasks is often sensitive in terms of privacy. Our initial proposal is a federated edge learning strategy based on real-world scenarios, which combines blurred data or pseudo shared data. Federated learning is used to train device models with the aim of protecting privacy while enabling mobile devices to more effectively utilize data for decision-making. In the case of limited energy on mobile devices, we propose a federated edge learning algorithm with blurred data sharing. This algorithm can generate more accurate models by uploading partially blurred data. In order to further improve model accuracy and protect privacy of mobile devices, we propose a federated edge learning algorithm with pseudo data sharing based on dataset distillation and generative adversarial networks (GANs) in scenarios with relatively sufficient energy. The experimental results on several traditional datasets show that our proposed algorithms outperform traditional algorithms in terms of accuracy and energy consumption.

Privacy-preserving Federated Learning (FL) based on Differential Privacy (DP) protects clients’ data by adding DP noise to samples’ gradients and has emerged as a de facto standard for data privacy in FL. However, the accuracy of global models in DP-based FL may be reduced significantly when rogue clients occur who deviate from the preset DP-based FL approaches and selfishly inject excessive DP noise beyond expectations, thereby applying a smaller privacy budget in the DP mechanism to ensure a higher level of security. Existing DP-based FL fails to prevent such attacks as they are imperceptible. Under the DP-based FL system and random Gaussian noise, the local model parameters of the rogue clients and the honest clients have identical distributions. In particular, the rogue local models show a low performance, but directly filtering out lower-performance local models compromises the generalizability of global models, as local models trained on scarce data also behave with low performance in the early epoch. In this paper, we propose ReFL, a novel privacy-preserving FL system that enforces DP and avoids the accuracy reduction of global models caused by excessive DP noise of rogue clients. Based on the observation that rogue local models with excessive DP noise and honest local models trained on scarce data have different performance patterns in long-term training epochs, we propose a long-term contribution incentives scheme to evaluate clients’ reputations and identify rogue clients. Furthermore, we design a reputation-based aggregation to avoid the damage of rogue clients’ models on the global model accuracy, based on the incentive reputation. Extensive experiments demonstrate ReFL guarantees the global model accuracy performance 0.77% - 81.71% higher than existing DP-based FL methods in the presence of rogue clients.