The integration of Internet of Things (IoT) devices in healthcare has enhanced medical efficiency but poses challenges such as data privacy risks and internal abuse. Traditional IoT data access frameworks suffer from centralization, limited scalability, and static permission controls. To address these issues, we propose MedAccessX, a blockchain-based access control framework combining attribute-based access control (ABAC) and role-based access control (RBAC). MedAccessX utilizes four types of smart contracts: a user management contract (UMC) for managing user operations, a medical data management contract (MDMC) for handling data, a policy contract (PC) for managing access rights, and an access control contract (ACC) for enforcing permissions and facilitating data sharing. Our evaluation, conducted on a private Ethereum blockchain network with multiple nodes, assesses security, deployment cost, gas consumption, throughput, and response time. Comparative analysis demonstrates that MedAccessX achieves lower deployment costs and higher throughput, outperforming existing solutions.
Federated learning (FL) is an emerging paradigm that enables multiple clients to collaboratively train a machine learning (ML) model without the need to exchange their raw data. However, it relies on a centralized authority to coordinate participants’ activities. This not only interrupts the entire training task in case of a single point of failure, but also lacks an effective regulatory mechanism to prevent malicious behavior. Although blockchain, with its decentralized architecture and data immutability, has significantly advanced the development of FL, it still struggles to withstand poisoning attacks and faces limitations in computational scalability. We propose Zkfhed, a verifiable and scalable FL system that overcomes the limitations of blockchain-based FL in poison attacks and computational scalability. First, we propose a two-stage audit scheme based on zero-knowledge proofs (ZKPs), which verifies that the training data are extracted from trusted organizations and that computations on the data exactly follow the specified training protocols. Second, we propose a homomorphic encryption delegation learning (HEDL), based on fully homomorphic encryption (FHE). It is capable of outsourcing complex computing to external computing resources without sacrificing the client's data privacy. Final, extensive experiments on real-world datasets demonstrate that Zkfhed can effectively identify malicious clients and is highly efficient and scalable in terms of online time and communication efficiency.
With the development of communication infrastructure and the popularity of smart devices, e-commerce is presenting in more diverse forms and attracting the attention of more and more users. Since e-commerce transactions usually involve sensitive information of a large number of users, privacy and security have become increasingly important issues. Despite certain advantages (e.g., trading security), the privacy protection capability and efficiency of blockchain is still limited by some key factors, especially of its architecture. In this paper, we propose a blockchain-based privacy protection system named PBTMS that integrates zero-knowledge proofs, hybrid encryption, and Pedersen commitments as foundational mechanisms to ensure robust privacy protection for transaction data and user information. To achieve secure, reliable, and efficient e-commerce transactions, the PBTMS employs blockchain technology and consensus mechanisms to enable distributed storage, thereby mitigating single points of failure and addressing the risks posed by malicious nodes. Moreover, by integrating on-chain storage with off-chain computation, the system substantially reduces blockchain-related overheads, including processing time, gas consumption, and storage costs. This design establishes the PBTMS as a highly adaptable and efficient system for the evolving requirements of secure and privacy-preserving e-commerce platforms. Theoretical analysis and experimental validation demonstrate that PBTMS reduces decryption and authentication times by 79.2% and 52.6%, respectively, while cutting encrypted data size by 52.5% and overall gas consumption by 55.4%, outperforming state-of-the-art solutions. These results indicate that PBTMS is a reliable and efficient system for secure e-commerce transaction platforms and provides a novel approach to enhancing privacy protection in e-commerce.
As artificial intelligence (AI) becomes integral to microservices deployed across multi-cloud environments, ensuring secure and scalable observability is critical. Traditional centralized observability methods often fail to address the privacy, compliance, and performance challenges inherent to distributed AI systems. This paper presents a federated learning–based framework for AI observability that preserves data privacy and scalability across heterogeneous cloud platforms. The proposed framework decentralizes telemetry collection and analysis by integrating local observability agents with secure federated aggregation, while maintaining interoperability with modern DevOps pipelines. We evaluate the architecture through case studies in retail, healthcare, and finance sectors, demonstrating improvements in anomaly detection, regulatory compliance, and operational efficiency. Additionally, the paper examines ethical considerations such as data privacy, fairness, and transparency, and outlines future directions including edge observability, privacy-enhanced computation, and automated governance. This research provides a foundational strategy for building trustworthy and efficient observability systems tailored to AI-powered microservices within complex multi-cloud ecosystems. Traditional observability methods struggle with privacy and performance in AI-powered multi-cloud microservices. We propose a federated learning–based framework that enables decentralized telemetry monitoring while ensuring compliance and scalability. Our evaluation across healthcare, finance, and retail shows improvements in anomaly detection latency (25%), fraud detection accuracy (18%), and GDPR/HIPAA alignment. This work lays the groundwork for trustworthy and efficient AI observability in complex cloud-native ecosystems.
Property transactions in the UK are increasingly adopting blockchain technology to enhance efficiency, transparency, and security. However, the inherent transparency of blockchain raises significant data privacy risks and regulatory compliance challenges, particularly under the UK General Data Protection Regulation (UK GDPR). This study examines the role of Zero-Knowledge Proofs (ZKPs) in addressing these concerns by enabling transaction validation while preserving confidentiality. Using entropy measures, k-anonymity analysis, and logistic regression, this research quantitatively assesses the privacy risks, effectiveness of ZKPs, and regulatory acceptance in blockchain-based property transactions. The findings reveal that 65.5% of transactions remain highly or moderately identifiable, posing privacy vulnerabilities under UK data protection laws. ZKP-enabled transactions significantly enhance confidentiality, achieving a 92.5% transaction privacy score, compared to 48.3% for non-ZKP transactions. However, these privacy gains come at a 67.8% increase in transaction costs, highlighting a critical trade-off between security and efficiency. Regulatory approval rates for ZKP-based blockchain platforms stand at 72.5%, suggesting a strong potential for compliance advantages. While ZKPs improve privacy and regulatory alignment, challenges remain in terms of computational overhead, transaction costs, and adoption barriers. To facilitate large-scale implementation, this study recommends optimizing zk-Rollups for efficiency, developing clear policy frameworks, and enhancing collaboration between regulators, industry stakeholders, and blockchain developers. These steps are essential to ensuring a balance between privacy, scalability, and compliance, paving the way for secure and legally sound blockchain-based property transactions in the UK.
The arrival of Machine Learning (ML) completely changed how we can unlock valuable information from data. Traditional methods, where everything was stored in one place, had big problems with keeping information private, handling large amounts of data, and avoiding unfair advantages. Machine Learning has become a powerful tool that uses Artificial Intelligence (AI) to overcome these challenges. We started by learning the basics of Machine Learning, including the different types like supervised, unsupervised, and reinforcement learning. We also explored the important steps involved, such as preparing the data, choosing the right model, training it, and then checking its performance. Next, we examined some key challenges in Machine Learning, such as models learning too much from specific examples (overfitting), not learning enough (underfitting), and reflecting biases in the data used. Moving beyond centralized systems, we looked at decentralized Machine Learning and its benefits, like keeping data private, getting answers faster, and using a wider variety of data sources. We then focused on a specific type called federated learning, where models are trained without directly sharing sensitive information. Real-world examples from healthcare and finance were used to show how collaborative Machine Learning can solve important problems while still protecting information security. Finally, we discussed challenges like communication efficiency, dealing with different types of data, and security. We also explored using a Zero Trust framework, which provides an extra layer of protection for collaborative Machine Learning systems. This approach is paving the way for a bright future for this groundbreaking technology.
This article presents a novel framework for decentralized artificial intelligence model training that combines federated learning with blockchain technology in cloud environments. By integrating these cutting-edge technologies, the article addresses critical challenges in collaborative AI development, including data privacy, secure model sharing, and participant incentivization. The article framework leverages Zero Knowledge Proofs (ZKPs) for enhanced privacy guarantees while utilizing blockchain-based smart contracts to ensure transparent and automated governance of the training process. The implementation demonstrates significant improvements in data transfer efficiency, privacy preservation, system reliability, and participant diversity compared to traditional centralized approaches. The results validate the effectiveness of combining federated learning with blockchain technology for secure, scalable, and efficient distributed AI model training.
This work presents a mathematical solution to data privacy and integrity issues in Split Learning which uses Homomorphic Encryption (HE) and Zero-Knowledge Proofs (ZKP). It allows calculations to be conducted on encrypted data, keeping the data private, while ZKP ensures the correctness of these calculations without revealing the underlying data. Our proposed system, HavenSL, combines HE and ZKP to provide strong protection against attacks. It uses Discrete Cosine Transform (DCT) to analyze model updates in the frequency domain to detect unusual changes in parameters. HavenSL also has a rollback feature that brings the system back to a verified state if harmful changes are detected. Experiments on CIFAR-10, MNIST, and Fashion-MNIST datasets show that using Homomorphic Encryption and Zero-Knowledge Proofs during training is feasible and accuracy is maintained. This mathematical-based approach shows how crypto-graphic can protect decentralized learning systems. It also proves the practical use of HE and ZKP in secure, privacy-aware collaborative AI.
With the growing demand for secure, decentralized file sharing solutions, this study presents a blockchain and IPFS-based framework for efficient data storage and access control. The proposed system leverages asymmetric encryption, smart contracts, and distributed access management to ensure confidentiality and integrity. The files are encrypted using AES-256 before they are stored in IPFS, and SHA-256 hashing is used to verify the content. Access control is guaranteed using blockchain-based policies, encrypting access keys and dynamic permissions to ensure that users can exchange files. An intelligent contract automates authentication, access and distribution of keys, minimizing dependence on centralized bodies. In addition, suppliers of storage facilities for an incentive mechanism reward the economy of economic and scalable storage. By using consensus mechanisms, such as proof of aspiration (POS) or proof of the authorities (POA), the system prevents unauthorized modifications and increases data security. This approach provides a reliable solution for organizations requiring controlled access to confidential data, with potential applications in the field of financial, health care and public sectors.
Lucien K. L. Ng, Pedro Moreno-Sánchez, Mohsen Minaei, Panagiotis Chatzigiannis · 6 authors
Zero-Knowledge Succinct Non-Interactive Argument of Knowledge (zk-SNARK) schemes have gained significant adoption in privacy-preserving applications, decentralized systems (e.g., blockchain), and verifiable computation due to their efficiency. However, the most efficient zk-SNARKs often rely on a one-time trusted setup to generate a public parameter, often known as the ``Powers of Tau" (PoT) string. The leakage of the secret parameter, $τ$, in the string would allow attackers to generate false proofs, compromising the soundness of all zk-SNARK systems built on it. Prior proposals for decentralized setup ceremonies have utilized blockchain-based smart contracts to allow any party to contribute randomness to $τ$ while also preventing censorship of contributions. For a PoT string of $d$-degree generated by the randomness of $m$ contributors, these solutions required a total of $O(md)$ on-chain operations (i.e., in terms of both storage and cryptographic operations). These operations primarily consisted of costly group operations, particularly scalar multiplication on pairing curves, which discouraged participation and limited the impact of decentralization In this work, we present Lite-PoT, which includes two key protocols designed to reduce participation costs: \emph{(i)} a fraud-proof protocol to reduce the number of expensive on-chain cryptographic group operations to $O(1)$ per contributor. Our experimental results show that (with one transaction per update) our protocol enables decentralized ceremonies for PoT strings up to a $2^{15}$ degree, an $\approx 16x$ improvement over existing on-chain solutions; \emph{(ii)} a proof aggregation technique that batches $m$ randomness contributions into one on-chain update with only $O(d)$ on-chain operations, independent of $m$. This significantly reduces the monetary cost of on-chain updates by $m$-fold via amortization.
This comprehensive article explores recent advancements in privacy-preserving technologies within artificial intelligence systems, focusing on five key approaches: federated learning, differential privacy, homomorphic encryption, privacy-preserving machine learning (PPML), and zero-knowledge proofs. The article examines how these technologies address critical privacy challenges in machine learning environments while maintaining model performance and utility. The article highlights the implementation of these approaches across various domains, particularly in healthcare and financial services, demonstrating their effectiveness in protecting sensitive data throughout the machine learning lifecycle. The article reveals how these technologies complement each other to create robust privacy protection frameworks while enabling organizations to leverage the power of AI without compromising data confidentiality.
Abstract Federated Learning (FL) is a promising form of distributed machine learning that preserves privacy by training models locally without sharing raw data. While FL ensures data privacy through collaborative learning, it faces several critical challenges. These include vulnerabilities to reverse engineering, risks to model architecture privacy, susceptibility to model poisoning attacks, threats to data integrity, and the high costs associated with communication and connectivity. This paper presents a comprehensive review of FL, categorizing data partitioning formats into horizontal federated learning, vertical federated learning, and federated transfer learning. Furthermore, it explores the integration of FL with blockchain, leveraging blockchain’s decentralized nature to enhance FL’s security, reliability, and performance. The study reviews existing FL models, identifying key challenges such as privacy risks, communication overhead, model poisoning vulnerabilities, and ethical dilemmas. It evaluates privacy-preserving mechanisms and security strategies in FL, particularly those enabled by blockchain, such as cryptographic methods, decentralized consensus protocols, and tamper-proof data logging. Additionally, the research analyzes regulatory and ethical considerations for adopting blockchain-based FL solutions. Key findings highlight the effectiveness of blockchain in addressing FL challenges, particularly in mitigating model poisoning, ensuring data integrity, and reducing communication costs. The paper concludes with future directions for integrating blockchain and FL, emphasizing areas such as interoperability, lightweight consensus mechanisms, and regulatory compliance.
Abstract As machine learning technologies advance rapidly across various domains, concerns over data privacy and model security have grown significantly. These challenges are particularly pronounced when models are trained and deployed on cloud platforms or third-party servers due to the computational resource limitations of users’ end devices. In response, zero-knowledge proof (ZKP) technology has emerged as a promising solution, enabling effective validation of model performance and authenticity in both training and inference processes without disclosing sensitive data. Thus, ZKP ensures the verifiability and security of machine learning models, making it a valuable tool for privacy-preserving AI. Although some research has explored the verifiable machine learning solutions that exploit ZKP, a comprehensive survey and summary of these efforts remains absent. This survey paper aims to bridge this gap by reviewing and analyzing all the existing Zero-Knowledge Machine Learning (ZKML) research from June 2017 to August 2025. We begin by introducing the concept of ZKML and outlining its ZKP algorithmic setups under three key categories: verifiable training, verifiable inference, and verifiable testing. Next, we provide a comprehensive categorization of existing ZKML research within these categories and analyze the works in detail. Furthermore, we explore the implementation challenges faced in this field and discuss the improvement works to address these obstacles. Additionally, we highlight several commercial applications of ZKML technology. Finally, we propose promising directions for future advancements in this domain.
This paper explores the integration of blockchain technology and smart contracts in the development of nextgeneration digital identity solutions. As the demand for secure, privacy-preserving, and user-centric identity management systems increases, blockchain and smart contracts offer a promising framework that enhances transparency, automation, and user control. We outline the methodology employed to assess the effectiveness of blockchain and smart contracts in digital identity management, focusing on aspects such as security, interoperability, and user empowerment. Through comprehensive data analysis, we present the results of our study, demonstrating the potential benefits and challenges associated with implementing blockchain-based identity systems augmented by smart contracts. Our findings contribute to the ongoing discourse on digital identity and provide insights for future research and practical applications.
Abstract Smart agriculture promises to alleviate the burden of climate risks on crop production by leveraging machine learning tasks. These tasks act as a decision support instrument for making well-informed choices by stakeholders in the agricultural value chain. Currently, predictive models in smart agriculture demand a centralized collection of diverse data, fragmented across multiple information systems leading to a single point of failure. The application of the Federated Learning (FL) technique restricts the movement of raw data and trains the model at the data source. However, the FL approach does not ensure trust factors like privacy, authentication, data provenance, transparency and traceability. To address this, a decentralized federated learning framework built on blockchain can be a potential solution. In this study, we introduce a blockchain-based framework called AgriFLChain for trusted federated learning in the context of smart agriculture. We focus on crop yield prediction as an illustrative use case, initially discussing centralized deep learning models (ResNet-16, ResNet-28, CNN-DNN, and CNN-LSTM). We then detail the authentication and data provenance mechanisms for federated learning participants, utilizing blockchain-based Decentralized Identifiers (DIDs) and Verifiable Credentials (VCs). We implement these models using vanilla federated learning and Differential Privacy (DP) federated learning approaches, achieving transparency and traceability through smart contracts by recording metadata of model updates into the blockchain. Finally, detailed evaluation demonstrates that AgriFLChain achieves comparable efficiency to centralized models while maintaining scalability in blockchain transactions for higher data volumes.
The integration of Internet of Things (IoT) devices in healthcare has revolutionized patient care by enabling real-time monitoring, personalized treatments, and efficient data management. However, this technological advancement introduces significant security risks, particularly concerning the confidentiality, integrity, and availability of sensitive medical data. Traditional security measures are often insufficient to address the unique challenges posed by IoT environments, such as heterogeneity, resource constraints, and the need for real-time processing. To tackle these challenges, we propose a comprehensive three-phase security framework designed to enhance the security and reliability of IoT-enabled healthcare systems. In the first phase, the framework assesses the reliability of IoT devices using a reputation-based trust estimation mechanism, which combines device behavior analytics with off-chain data storage to ensure scalability. The second phase integrates blockchain technology with a lightweight proof-of-work mechanism, ensuring data immutability, secure communication, and resistance to unauthorized access. The third phase employs a lightweight Long Short-Term Memory (LSTM) model for anomaly detection and classification, enabling real-time identification of cyber threats. Simulation results demonstrate that the proposed framework outperforms existing methods, achieving a 2% increase in precision, accuracy, and recall, a 5% higher attack detection rate, and a 3% reduction in false alarm rate. These improvements highlight the framework's ability to address critical security concerns while maintaining scalability and real-time performance.
This research introduces FoReChain (Fog-based Re-Encryption Chain), a blockchain-enabled proxy re-encryption (PRE) framework designed for secure, low-latency data sharing in fog-based IoT networks. The framework addresses key challenges related to data security, privacy, and performance in distributed environments, where traditional models face issues like high latency, limited scalability, and inefficient key management. FoReChain integrates blockchain with ECC-based proxy re-encryption to secure data without exposing original content. A delegated Practical Byzantine Fault Tolerance (d-PBFT) consensus mechanism ensures efficient transaction validation. The framework processes data at fog nodes, reducing delays commonly found in cloud-dependent models. Key management relies on time-based key updates stored immutably on the blockchain, while zero-knowledge proofs support secure, anonymous data sharing. The study evaluates FoReChain against FE-PRE and PREA models using metrics such as latency, throughput, scalability, blockchain consensus time, and adaptive policy effectiveness. Results show lower latency, higher throughput, and better adaptability in FoReChain, especially under heavy network conditions like smart healthcare and industrial IoT setups. FoReChain demonstrates secure data sharing, efficient resource utilization, and reliable key management in dynamic IoT environments. It offers consistent performance under varying loads, with improved scalability and data integrity maintained through decentralized validation.
Blockchain technology, with its decentralization as well as tamper-proof characteristics, has achieved wide application in major fields in recent years. However, because of the potential of privacy leakage that comes with its transparency, privacy protection technology has emerged as a key area of current blockchain research. The first step involves reviewing the blockchain's architecture and selecting a summary of the privacy threats posed by the four layers of the blockchain: data, network, transaction, and application. Next, it concentrates on describing the two more significant types of blockchain privacy protection technology: zero-knowledge proof and homomorphic encryption. The former is developed from its fundamental ideas, application scenarios in the blockchain, and performance and security analysis. Conversely, zero-knowledge proof is derived from three from three aspects of its basic concept, application in blockchain, and technical challenges; finally, the privacy protection technology in blockchain is summarized and a prediction of its future research direction development is made.
One of the goals of Federated Learning (FL) is to collaboratively train a global model using local models from remote participants. However, the FL process is susceptible to various security challenges, including interception and tampering models, information leakage through shared gradients, and privacy breaches that expose participant identities or data, particularly in sensitive domains such as medical environments. Furthermore, the advent of quantum computing poses a critical threat to existing cryptographic protocols through the Shor and Grover algorithms, causing security concerns in the communication of FL systems. To address these challenges, we propose a Post-Quantum Blockchain-based protocol for Federated Learning (PQBFL) that utilizes post-quantum cryptographic (PQC) algorithms and blockchain to enhance model security and participant identity privacy in FL systems. It employs a hybrid communication strategy that combines off-chain and on-chain channels to optimize cost efficiency, improve security, and preserve participant privacy while ensuring accountability for reputation-based authentication in FL systems. The PQBFL specifically addresses the security requirement for the iterative nature of FL, which is a less notable point in the literature. Hence, it leverages ratcheting mechanisms to provide forward secrecy and post-compromise security during all the rounds of the learning process. In conclusion, PQBFL provides a secure and resilient solution for federated learning that is well-suited to the quantum computing era.
Federated Learning (FL) enables collaborative model training without sharing raw data, preserving privacy while harnessing distributed datasets. However, traditional FL systems often rely on centralized aggregating mechanisms, introducing trust issues, single points of failure, and limited mechanisms for incentivizing meaningful client contributions. These challenges are exacerbated as FL scales to train resource-intensive models, such as large language models (LLMs), requiring scalable, decentralized solutions. This paper presents a blockchain-based FL framework that addresses these limitations by integrating smart contracts and a novel hybrid incentive mechanism. The framework automates critical FL tasks, including client registration, update validation, reward distribution, and maintaining a transparent global state. The hybrid incentive mechanism combines on-chain alignment-based rewards, off-chain fairness checks, and consistency multipliers to ensure fairness, transparency, and sustained engagement. We evaluate the framework through gas cost analysis, demonstrating its feasibility for different scales of federated learning scenarios.
Ye Liu, Yuqing Niu, Chengyan Ma, Ruidong Han · 8 authors
Smart contracts are highly susceptible to manipulation attacks due to the leakage of sensitive information. Addressing manipulation vulnerabilities is particularly challenging because they stem from inherent data confidentiality issues rather than straightforward implementation bugs. To tackle this by preventing sensitive information leakage, we present PartitionGPT, the first LLM-driven approach that combines static analysis with the in-context learning capabilities of large language models (LLMs) to partition smart contracts into privileged and normal codebases, guided by a few annotated sensitive data variables. We evaluated PartitionGPT on 18 annotated smart contracts containing 99 sensitive functions. The results demonstrate that PartitionGPT successfully generates compilable, and verified partitions for 78% of the sensitive functions while reducing approximately 30% code compared to function-level partitioning approach. Furthermore, we evaluated PartitionGPT on nine real-world manipulation attacks that lead to a total loss of 25 million dollars, PartitionGPT effectively prevents eight cases, highlighting its potential for broad applicability and the necessity for secure program partitioning during smart contract development to diminish manipulation vulnerabilities.
Mohammed Shalan, Md Rakibul Hasan, Yan Bai, Juan Li
The increasing adoption of smart home devices has raised significant concerns regarding privacy, security, and vulnerability to cyber threats. This study addresses these challenges by presenting a federated learning framework enhanced with blockchain technology to detect intrusions in smart home environments. The proposed approach combines knowledge distillation and transfer learning to support heterogeneous IoT devices with varying computational capacities, ensuring efficient local training without compromising privacy. Blockchain technology is integrated to provide decentralized, tamper-resistant access control through Role-Based Access Control (RBAC), allowing only authenticated devices to participate in the federated learning process. This combination ensures data confidentiality, system integrity, and trust among devices. This framework’s performance was evaluated using the N-BaIoT dataset, showcasing its ability to detect anomalies caused by botnets such as Mirai and BASHLITE across diverse IoT devices. Results demonstrate significant improvements in intrusion detection accuracy, particularly for resource-constrained devices, while maintaining privacy and adaptability in dynamic smart home environments. These findings highlight the potential of this blockchain-enhanced federated learning system to offer a scalable, robust, and privacy-preserving solution for securing smart homes against evolving threats.