Blockchain has the potential to be a game changer in the way health records are managed; it's secure, transparent and decentralized. Legacy EHR systems are plagued with data breaches, and interoperability challenges, as well as a central point of failure. Blockchain addresses these risks through its public ledger, cryptographic encoding, and consensus-driven verification, which all contribute to making health records tamper-resistant and auditable. Smart contracts automate access control so that you can share patient data with other authorized parties securely and in line with HIPAA or GDPR. The decentralized nature of blockchain also eliminates single points of failure, which mitigates the risk of hacking and unauthorized access. Further, blockchain promotes interoperation through normalization in data formats, such as Fast Healthcare Interoperability Resources (FHIR), and facilitates the sharing of data between institutions while preserving privacy. Scalability solutions in the form of sharding and layer-2 protocols allow large-scale medical data to be processed in a decentralized manner while new consensus algorithms (e.g., Proof-of-Stake) keep energy consumption down. Much like transportation, there are some key challenges, such as regulatory adherence and compatibility with existing systems. Still, if used properly, blockchain could serve as a transparent, secure, and patient-centric model for health record management. New developments in post-quantum cryptography, AI-platform deeds and smart contracts will continue to reinforce blockchain's contribution to disrupting healthcare data management.
This tutorial provides a detailed and structured examination of the latest developments in data engineering and blockchain technologies, focusing on their convergence with emerging telecommunication systems. A major focus is on mapping the data engineering lifecycle - including phases such as data connectivity, ingestion, processing and analysis, storage, visualization and orchestration - to the architecture and operational requirements of telecommunication networks. The role of blockchain and distributed ledger technologies (DLTs) in enabling secure, transparent and decentralized solutions for B5G systems is also highlighted. In addition, the tutorial explores the integration of these frameworks with data science pipelines and discusses practical use cases where data engineering and blockchain intersect in telecom environments. To complement the conceptual parts, two illustrative demonstrations are also presented.
Smart contracts are trustworthy, immutable, and automatically executed programs on the blockchain. Their execution requires the Gas mechanism to ensure efficiency and fairness. However, due to non-optimal coding practices, many contracts contain Gas waste patterns that need to be optimized. Existing solutions mostly rely on manual discovery, which is inefficient, costly to maintain, and difficult to scale. Recent research uses large language models (LLMs) to explore new Gas waste patterns. However, it struggles to remain compatible with existing patterns, often produces redundant patterns, and requires manual validation/rewriting. To address this gap, we present GasAgent, the first multi-agent system for smart contract Gas optimization that combines compatibility with existing patterns and automated discovery/validation of new patterns, enabling end-to-end optimization. GasAgent consists of four specialized agents, Seeker, Innovator, Executor, and Manager, that collaborate in a closed loop to identify, validate, and apply Gas-saving improvements. Experiments on 100 verified real-world contracts demonstrate that GasAgent successfully optimizes 82 contracts, achieving an average deployment Gas savings of 9.97%. In addition, our evaluation confirms its compatibility with existing tools and validates the effectiveness of each module through ablation studies. To assess broader usability, we further evaluate 500 contracts generated by five representative LLMs across 10 categories and find that GasAgent optimizes 79.8% of them, with deployment Gas savings ranging from 4.79% to 13.93%, showing its usability as the optimization layer for LLM-assisted smart contract development.
Hoang Viet Anh Le, Quoc Duy Nam Nguyen, Tadashi Nakano, Thi Hong Tran
The Blockchain-based Decentralized Identity Management System (BDIMS) is an innovative framework designed for digital identity management, utilizing the unique attributes of blockchain technology. The BDIMS categorizes entities into three distinct groups: identity providers, service providers, and end-users. The system’s efficiency in identifying and extracting information from identification cards is enhanced by the integration of artificial intelligence (AI) algorithms. These algorithms decompose the extracted fields into smaller units, facilitating optical character recognition (OCR) and user authentication processes. By employing Merkle Trees, the BDIMS ensures secure authentication with service providers without the need to disclose any personal information. This advanced system empowers users to maintain control over their private information, ensuring its protection with maximum effectiveness and security. Experimental results confirm that the BDIMS effectively mitigates identity fraud while maintaining the confidentiality and integrity of sensitive data.
Ovaj rad istražuje teorijske temelje i praktičnu primjenu dokaza nultog znanja u blockchain sustavima, s fokusom na Polygon zkEVM blockchain. Analiziraju se zk-SNARK i zk-STARK sustavi dokazivanja te njihova implementacija u ZK-rollup rješenjima za poboljšanje skalabilnosti blockchain mreža. Teorijska analiza pokazuje kako dokazi nultog znanja omogućavaju verifikaciju transakcija bez otkrivanja osjetljivih podataka, čime se adresiraju izazovi privatnosti i skalabilnosti. Praktični dio uključuje implementaciju decentralizirane aplikacije za glasovanje na Polygon zkEVM Cardona Testnet mreži, demonstrirajući primjenu tehnologije u realnoj situaciji. Analiza transakcijskih podataka potvrđuje značajne uštede goriva kroz batch procesiranje transakcija u odnosu na direktno izvršavanje na Ethereum glavnom lancu. Rad identificira ključne prednosti i ograničenja trenutnih implementacija te predlaže smjerove za buduća istraživanja u području post-kvantne kriptografije i hardverske akceleracije.
<p dir="ltr"><b>Advances in Identity and Access Management (IAM): Systematic Insights into AI, Blockchain, and Zero Trust Architectures</b> <p dir="ltr">In an era of expanding digital infrastructure, cloud computing, and remote work, robust Identity and Access Management (IAM) systems are critical for securing sensitive data and ensuring regulatory compliance. This research paper provides a comprehensive systematic review of recent advancements in IAM technologies, addressing the limitations of traditional centralized systems, such as single points of failure and privacy concerns. Utilizing the PRISMA methodology, the study analyzes five peer-reviewed articles from a pool of 23 retrieved from Scopus, published between 2021 and 2025. Key innovations explored include passwordless authentication, AI-driven adaptive authentication, Zero Trust architectures, decentralized identity (DID), self-sovereign identity (SSI), and privacy-enhancing cryptographic techniques like zero-knowledge proofs. The review highlights their applications in multi-cloud, IoT, and hybrid environments, emphasizing enhanced security, user experience, and interoperability. Challenges such as standardization gaps, implementation costs, and privacy concerns are discussed, alongside future directions, including universal protocols and IoT integration. A publicly accessible dataset (DOI: 10.5281/zenodo.12345678) ensures reproducibility. This work serves as an essential resource for cybersecurity researchers and practitioners seeking to navigate the evolving landscape of IAM technologies.
As the frequency and scope of major diseases continue to rise, the need for an efficient early warning and prevention system in public health has become increasingly urgent. This paper addresses the challenges of preventing and predicting high-frequency and sudden-onset diseases, and proposes a blockchain-based solution to construct a trusted data space. The solution integrates blockchain technology with trusted data space construction, effectively addressing the challenges of data sharing and utilization across regions, departments, and business domains for disease warning and prevention. The experiment showed that the solution on-chain TPS(Transactions Per Second) for spatial data is 1318.7, and the single-node QPS(Queries Per Second) is 1999.2. It meets the requirements for handling high-frequency and sudden public health events, and offers certain advantages in data security, sharing efficiency, and privacy protection. Future research will continue to explore the deep integration and extended applications of cross - chain technology, zero - knowledge proof, and other privacy -preserving computing technologies.
M. Sukanya, R. Balasubramaniyan, V. Samuthira Pandi, Thaer Ahmad Abu-Saleem · 6 authors
The combination of Artificial Intelligence (AI) and blockchain has great potential to solve centralized challenges, including but not limited to scalability and energy effectiveness, as demonstrated by this paper. Traditional consensus algorithms including PoW and PoS have been under severe criticism for being slow and tremendously energy consuming. With increasing size and complexity of blockchain networks, the demand for improved consensus mechanisms that can operation at reduced computation costs, and associated energy consumption, has become critical. In a recent research, a Mechanism integrated Artificial Intelligence (AI) Techniques which is designed to improve the Blockchain performance especially in scalability and energy efficiency is introduced. The suggested architecture embeds machine learning algorithms to dynamically tune consensus decisions according to network status, transaction influx, and computing power. Using AI, it can anticipate network congestion and adapt block size, mining difficulty, and transaction priority accordingly for higher throughput and lower energy consumption. In addition, AI-powered anomaly detection algorithms can detect potential security threats or fraudulent behaviors and increase the overall trustworthiness of the block chain. This adaptive method enables blockchain networks to rapidly scale without sacrificing security, a necessity as the technology expands to include new applications across industries and in applications from financial transactions to supply chain management. Research also investigates the possibility of hybrid consensus models that mix traditional consensus models with AI-enabled models in order to design more efficient and secure frameworks. These hybrid designs combine AI with PoW, PoS or Byzantine Fault Tolerance (BFT) to better compromise among decentralization, scalability, and energy consumption. The AI elements permit real-time decision-making for the network, and can respond rapidly to changing conditions, leading to enhancement of overall system performance. By experimentations and simulations, this paper proves AI-enabled consensus mechanisms can make traditional systems inferior to them in the energy consumption and transaction speed.
Blockchain technology plays a crucial role for numerous decentralized applications and cryptocurrencies. Still, there are many networks that rely on incompetent and unmanageable consensus mechanisms. This paper proposes an improved Round Robin Proof of Stake consensus protocol as a solution for the restrictions of outdated Proof of Work (PoW) and Proof of Stake (PoS) systems. By using Python simulation, we examine the validator’s behavior, energy efficiency, and fairness in the consensus protocol. Our discoveries reveal that RR-PoS significantly helps in improving the efficiency and encourages unbiased participation of validators, designing it as an innovative solution for blockchain consensus. Python helps in allowing preciseness to the RR-PoS model that helps in integrating important features, i.e., validator rotation, energy modeling of RR-PoS, and incorporating essential features like validator rotation, cooldown periods, and energy-aware block proposals. The comprehensive approach of this enables close monitoring of validator interactions and ensures fair opportunity distribution. Ultimately, RR-PoS emerges as a compelling and sustainable consensus alternative for future blockchain networks.
Dilli Ganesh, T J Nandhini, Amer Ibrahim, Ahmed A. Elngar · 5 authors
With the current prevalence of digitization of health care records comes the issues of data privacy, security, and interoperability typical in traditional health information systems. This paper proposes a Blockchain-Powered Secure Health Data Exchange that utilizes smart contracts, cryptographic algorithms (AES-256, ECDSA), and a decentralized ledger to improve patient privacy and interoperability. This paper presents a novel blockchain-based monitoring mechanism tailored for EHRs: RUDDER—real-time, universal, decentralized, distributed, and enciphered data regulation for EHRs. Using role-based access control (RBAC) and zero-knowledge proofs (ZKP), the architecture prevents unauthorized access in our patient-centric model. This approach enabled the Practical Byzantine Fault Tolerance (PBFT) consensus mechanism, which offers high transaction throughput and latency. In addition, we create an interoperability layer that is FHIR compliant and allows for continued data exchange between the hospitals, research institutions, and the insurer. Experimental results show that significant gains have been achieved with a 500% increase in scalability, 99.6% lower operational costs, and 90% lower energy consumption compared to their conventional counterparts. The new framework that was proposed is a scalable, secure, and cost-effective solution for next-generation healthcare data management. The future work will cover AI-based anomaly detection and quantum-resistant cryptography that can improve security and efficiency.
Ashu Nayak, S. Sivasubramanian, Anil Sharma, Hasan M. Madi · 7 authors
The rising need for safe and privacy-preserving digital identity verification has exposed the limits of previous methods, which typically involve personal information. These technologies risk users' privacy owing to data leaks and user-centric management issues. Due to these problems, this article presents ZK-VerifyChain, a blockchain-based Zero-Knowledge-based Verification system. The proposed ZK-VerifyChain uses permissioned blockchain smart contracts and non-interactive zero-knowledge proofs to verify identities securely. With this design, users can identify themselves without giving personal information. The suggested technique was tested in a virtual environment for computational overhead, scalability, and verification time. Testing has demonstrated that the ZK-Verify Chain is effective, fast, and secure against manipulation and identity theft. The blockchain layer provides immutability, transparency, and decentralized trust management. The suggested ZK-VerifyChain moves us closer to user-controlled, secure digital identity systems by providing a scalable, privacy-centric digital identity verification solution. The experimental results show an average verification time of 12.4 ms compared to other methods.
Hiba Akli, Igor Stéphan, Karim Zkik, Sofiane Hamrioui
E-health systems have revolutionized healthcare by enabling efficient data sharing and management. However, they face significant security and privacy challenges, including unauthorized access, data breaches, identity fraud, and insurance fraud. Existing solutions attempt to address these issues but suffer from single points of failure, lack of patient-defined access control, and inadequate privacy-preserving mechanisms. This paper proposes a dual-blockchain architecture integrated with Self-Sovereign Identity and Zero-Knowledge Proofs to enhance security, privacy, and fraud resilience. The framework employs Decentralized Identifiers and Verifiable Credentials for secure authentication while leveraging the InterPlanetary File System for decentralized Electronic Health Records storage. By addressing the limitations of current systems, the proposed solution ensures a more secure, scalable, and privacy-preserving e-health environment.
Hengxin Lei, Thein Lai Wong, Tong Ming Lim, Xiangfu Zhao · 6 authors
Smart contracts, an important component of blockchain technology, have received widespread attention due to their decentralized and trustworthy characteristics. However, the security vulnerabilities of smart contracts pose a serious threat to their reliability, causing huge economic losses to users. Existing analysis tools are used to detect security vulnerabilities in smart contracts. However, due to their excessive reliance on hard rules defined by experts when detecting vulnerabilities in smart contracts, the time to perform the detection significantly increases as the complexity of smart contracts increases. In this study, we developed a novel hybrid machine learning model called Bi-CUR. The Bi-CUR model extracts the feature matrix of smart contract opcodes through Bigram and detects smart contract vulnerability through CUR matrix decomposition. It approximates the original matrix by selecting rows and columns, thereby reducing computational complexity while maintaining the features of the data. Compared with traditional vulnerability detection methods, models based on CUR matrix decomposition showed higher efficiency and accuracy. In addition, the model ensured interpretability, which makes it applicable to different types of smart contract vulnerability detection.
With the widespread application of Transportation Cyber Physical Systems (T-CPS), increasingly intelligent and interconnected vehicles are conducting extensive transportation activities. Compared with traditional transportation equipment, they integrate advanced information functions such as data collection, terminal communication, real-time computing, and remote coordination, which can generate and collect a large amount of real traffic data. The enormous value of these traffic data can be released through market-oriented transactions. Blockchain technology can support the transmission and collaborative control of information T-CPS, while protecting the privacy and data security of intelligent connected vehicles. This article proposes a blockchain based data trading system aimed at simplifying the transaction flow of traffic data for intelligent connected vehicle owners, while maintaining fairness, privacy, and sustainable market development. Our work introduces two key innovations: a two-stage availability verification process that reduces transaction costs while enhancing data reliability, and an efficient encryption confirmation mechanism that ensures privacy and security for data providers and buyers throughout the entire transaction lifecycle. Finally, we demonstrate the feasibility and overall performance of our system through comprehensive analysis including security and reliability assessment, market behavior analysis, and computational complexity modeling, as well as practical experiments based on the Ethereum blockchain network. The evaluation results indicate that this scheme can provide privacy and security data transaction services at lower transaction costs.
Web3 technologies have experienced unprecedented growth in the last decade, achieving widespread adoption. As various blockchain networks continue to evolve, we are on the cusp of a paradigm shift in which they could provide services traditionally offered by the Internet, but in a decentralized manner, marking the emergence of the Internet of Blockchains. While significant progress has been achieved in enabling interoperability between blockchain networks, existing solutions often assume that networks are already mutually aware. This reveals a critical gap: the initial discovery of blockchain networks remains largely unaddressed. This paper proposes a decentralized architecture for blockchain network discovery that operates independently of any centralized authority. We also introduce a mechanism for discovering assets and services within a blockchain from external networks. Given the decentralized nature of the proposed discovery architecture, we design an incentive mechanism to encourage nodes to actively participate in maintaining the discovery network. The proposed architecture implemented and evaluated, using the Substrate framework, demonstrates its resilience and scalability, effectively handling up to 130,000 concurrent requests under the tested network configurations, with a median response time of 5.5 milliseconds, demonstrating the ability to scale its processing capacity further by increasing its network size.
The decentralized finance (DeFi) community has grown rapidly in recent years, pushed forward by cryptocurrency enthusiasts interested in the vast untapped potential of new markets. The surge in popularity of cryptocurrency has ushered in a new era of financial crime. Unfortunately, the novelty of the technology makes the task of catching and prosecuting offenders particularly challenging. Thus, it is necessary to implement automated detection tools related to policies to address the growing criminality in the cryptocurrency realm.
Bitcoin mining is highly energy-intensive, and improving its efficiency is critical for both economic and environmental sustainability. This project presents a web-based simulation tool that models key aspects of Bitcoin mining, including the SHA-256 hashing algorithm, nonce iteration, and target difficulty checks. The computational backend is integrated with real-time power and thermal models, enabling the simulator to reflect how hash rate influences energy consumption and temperature. Interactive controls for frequency, voltage, and resistance, along with graphical visualizations of power usage over time, allow users to explore trade-offs between energy efficiency and mining performance. The simulation also includes a financial trade-off analysis feature and supports extended runtime testing to evaluate long-term behavior under varying operational conditions.
Road-Side Units (RSUs) are deployed along the road to facilitate Vehicle-to-Infrastructure (V2I) communication, a critical component of Vehicle-to-Everything (V2X) services. However, the presence of rogue RSUs, which are unauthorized access points, poses significant threats to V2X communications and safety applications. These rogue RSUs, installed by adversaries, can mimic legitimate RSUs and establish connections with vehicles, enabling various attacks such as data interception, spoofing, and denial of service. Therefore, Software-defined Networking (SDN) has been leveraged to employ various traffic engineering, network management, and secure verification of RSUs and vehicle functionalities. The SDN controller (SDNC), which manages RSUs, can periodically verify their identity. This mechanism ensures the association of vehicles with legitimate RSUs and the detection of rogue RSUs. To periodically verify the RSUs' identity, a novel Fiat-Shamir Transformation-enabled Non-Interactive Zero-knowledge Proof ($\text{Z K P}$) -based identity verification mechanism has been proposed. The RSUs are initially registered with an SDNC in this protocol. Subsequently, SDNC verifies their identity periodically using a unique ZKP-based challenge-response mechanism. As per the performance and security analysis, the proposed protocol surpasses state-of-the-art authentication protocols and achieves notable improvements.
Ensuring software quality in the Web3 ecosystem presents unique challenges due to its decentralized architecture and evolving technical landscape. While international standards such as the SQuaRE (Systems and software Quality Requirements and Evaluation) framework offer structured approaches for quality assurance, they are often perceived as overly theoretical and not directly applicable to blockchain-based applications. This study aims to translate these standards into actionable practices suitable for Web3 environments, thereby supporting compliance and fostering stakeholder trust. Using the Design Science Research methodology, complemented by Lean Startup principles, a practical quality assurance guide was co-developed through collaboration between VOH.CoLAB researchers and the Exeedme project team and inspired by the practical experience in gaming and digital assets trading blockchain-based platforms. The resulting guide includes a structured framework comprising eight testing domains, 16 sub-domains and 108 targeted tests, with the domains addressing critical features of blockchain software, including, functional suitability, integration, security, performance, usability, portability, recoverability and resilience. This work contributes to the operationalization of international quality standards in decentralized technology, promoting more resilient and trustworthy blockchain applications.
Yingxuan Yang, Qiuying Peng, Jun Dan Wang, Ying Wen · 5 authors
Recent advances in large language models (LLMs) have enabled the development of LLM agents-autonomous systems capable of perceiving their environment, reasoning about tasks, and taking actions using external tools. While existing LLM-based Multi-Agent Systems (LaMAS) have shown promising results, they are predominantly centralized, operating within specific tasks or scenarios. These centralized designs simplify coordination but are fundamentally constrained by the limited data and knowledge available within a single entity. As LLM agents see broader deployment, the complexity of tasks increasingly requires collaboration across multiple organizations and data domains. Since organizations cannot and will not fully share their proprietary data, the next frontier of artificial intelligence lies in collective intelligence through decentralized LLM-based Multi-Agent Systems (LaMAS), where LLM agents, each accessing proprietary knowledge and tools, collaborate to solve complex tasks. This paradigm is becoming not just possible but necessary with the growing adoption of LLM agents across diverse organizations. This paper explores the transformative potential of decentralized LaMAS. In decentralized settings, two key issues arise: (1) privacy-preserving mechanisms that enable meaningful collaboration while safeguarding proprietary data and knowledge, and (2) monetization and credit attribution mechanisms that incentivize continuous improvement of agent capabilities and ensure fair value distribution among participants. Our analysis reveals that addressing these challenges can unlock a new paradigm of artificial collective intelligence that overcomes the limitations. This work contributes to decentralized AI by proposing a practical framework for mechanism design that advances both technological innovation and economic sustainability in decentralized LLM Agent networks.
Hope Leticia Nakayiza, Love Allen Chijioke Ahakonye, Dong‐Seong Kim, Jae‐Min Lee
Increased automation, connectivity, and data sharing enabled by 6G technology have heightened the vulnerability of Internet of Vehicles (IoV) networks. Addressing this challenge requires an intrusion detection system (IDS) capable of accurately identifying data falsification within IoV while adhering to real-time constraints. This paper presents a Blockchain-enhanced feature-engineered IDS to ensure precise attack detection and classification with minimal computational overhead in in-vehicle networks (IVNs). The proposed lightweight IDS utilizes a hybrid Pearson’s Correlation Coefficient (PCC) feature selection technique designed for deployment on the Telematics Control Unit (TCU). Furthermore, we propose a custom private blockchain network utilizing the proof of authority and association (PoA) consensus mechanism, deployable on the Roadside Unit (RSU), for the secure logging of vehicle Electronic Control Unit (ECU) information, detection results, and the automatic isolation of malicious ECUs via smart contracts. Experimentation analysis demonstrates that the proposed approach achieves notable performance, with a 99.9% detection accuracy and minimal computation times of 0.24s and 1.32s on the CICIoV2024 and CAN-Intrusion datasets. Furthermore, the system achieves high blockchain scalability, maintaining stable throughput of 16 tx/s and low transaction latency of 0.062s under increasing ECU density and RSU coverage.
Mutiullah Shaikh, Shafique Memon, Ali Ebrahimi, Uffe Kock Wiil
BACKGROUND: Healthcare information systems are hindered by delayed data sharing, privacy breaches, and lack of patient control over data. The growing need for secure, privacy-preserved access control interoperable in health informatics technology (HIT) systems appeals to solutions such as Blockchain (BC), which offers a decentralized, transparent, and immutable ledger architecture. However, its current adoption remains limited to conceptual or proofs-of-concept (PoCs), often relying on simulated datasets rather than validated real-world data or scenarios, necessitating further research into its pragmatic applications and their benchmarking. OBJECTIVE: This systematic literature review (SLR) aims to analyze BC-based healthcare implementations by benchmarking peer-reviewed studies and turning PoCs or production insights into real-world applications and their evaluation metrics. Unlike prior SLRs focusing on proposed or conceptual models, simulations, or limited-scale deployments, this review focuses on validating practical BC real-world applications in healthcare settings beyond conceptual studies and PoCs. METHODS: Adhering to PRISMA-2020 guidelines, we systematically searched five major databases (Scopus, Web of Science, PubMed, IEEE Xplore, and ScienceDirect) for high-precision relevant studies using MeSH terms related to BC in healthcare. The designed review protocol was registered with OSF, ensuring transparency in the review process, including study screening by independent reviewers, eligibility, quality assessment, and data extraction and synthesis. RESULTS: In total, 82 original studies fully met the eligibility criteria and narratively reported BC-based healthcare implementations with validated evaluation outcomes. These studies highlight the current challenges addressed by BC in healthcare settings, providing both qualitative and quantitative data synthesis on its effectiveness. CONCLUSIONS: BC-based healthcare implementations show both qualitative and quantitative effectiveness, with advancements in areas such as drug traceability (up to 100%) and fraud prevention (95% reduction). We also discussed the recent challenges of focusing more attention in this area, along with a discussion on the mythological consideration of our own work. Our future research should focus on addressing scalability, privacy-preservation, security, integration, and ethical frameworks for widespread BC adoption for data-driven healthcare.
The rapid growth of intelligent systems has raised significant concerns regarding data privacy and security. Traditional centralized machine learning approaches require data aggregation, increasing the risk of data breaches and regulatory violations. Federated Learning (FL) has emerged as a promising paradigm that enables collaborative model training while keeping data decentralized. This paper presents a comprehensive study of federated learning for privacy-preserving intelligent systems, highlighting its architecture, methodologies, applications, and challenges. The study also proposes an adaptive federated framework integrating secure aggregation and differential privacy. The findings demonstrate that federated learning significantly enhances privacy while maintaining model performance, making it suitable for healthcare, finance, and IoT applications.
Maryam Sarmad Mohammed Ali, Majid M. Manhosh, Ahmed Bahaaulddin A. Alwahhab, Faez Hlail Srayyih · 9 authors
This project examines the use of federated learning for financial forecasting, which focuses on a better prediction with privacy. Data aggregation in centralized models can break confidentiality, notably in finance. Our study offers a federated learning (FL) paradigm utilizing long short-term memory (LSTM) networks whereby diverse financial institutions collectively train strong forecasting models without data sharing. We employed NASDAQ-100 and S&P 500 datasets and utilized a differentially private LSTM network leveraging secure multiparty computing. The data reveal that performing an averaging federated (FedAvg) model was much superior to centralized and decentralized models with lower MAE and RMSE. The model's R2values of 0.92 show its ability to capture the market's complexity and perform well. This framework secures privacy and enables scalability for realtime financial forecasting. According to our findings, federated learning has the ability to substantially impact the banking industry and give an accurate and secure alternative to the existing approaches. Future studies will aim at including sophisticated privacy-preserving approaches and increasing model applications across varied financial datasets.