Blockchain Papers

Xin Liu, Hao Wang, Bo Zhang, Bin Zhang

No abstract is available for this record.

Mengke Zhang, Xiaohong Li, Jie Zhang, Zhé Hóu · 6 authors

As healthcare systems evolve and healthcare data grows, the need for cross-domain collaboration treatment has become more complex, necessitating fine-grained access control to enhance privacy and security. Blockchain provides a distributed trusted platform without third parties, but the current blockchain-based access control systems lack efficiency and sufficient privacy protection in cross-domain collaboration. To address these challenges, we propose SWIFTGUARD, an efficient and fine-grained access control system based on a master-slave chain to strengthen the security and privacy of cross-domain healthcare collaboration. SWIFTGUARD incorporates a zero-knowledge proof protocol for cross-domain authentication with-out exposing sensitive data and leverages quantitative attribute weights for efficient access control. Through game-based security proof, we demonstrate the zero knowledge and soundness of the system. Extensive experiments evaluate that SWIFTGUARD reduces the time complexity of access authorization from O($n$) to O(log$n$), with improved throughput and stable performance in cross-domain collaboration. Our comprehensive evaluation confirms that SWIFTGUARD provides a secure and efficient access control system for cross-domain healthcare collaboration.

Aditya Ranjan, Prabhat Kumar, Prabhat Kumar

A growing interest in the Internet of Things (IoT) is sustained by recent developments in networking cloud, edge computing, and big data processing. In today’s data-driven digital economy, IoT data security is quickly rising to the top of the value chain as it enables the development of numerous business models that offer a wide range of intelligent and pervasive services. But, if a suitable privacy-preserving mechanism is not in place these data, which, include sensitive personal information, may reveal the identities of related stakeholders. Remarkably, blockchain-based methods support the distributed nature of IoT while providing robust countermeasures to prevent data from being corrupted. This paper includes research papers that focus on blockchain technology and its key characteristics for Edge Computing privacy preservation. The research articles are analyzed by grouping them according to the blockchain-based privacy-preserving methods for edge IoT that were used in earlier studies. Additionally, the problems and research gaps found in the previous works are enumerated so that future researchers can improve their work and provide a solution. Software tools, technique classification, blockchain technologies, and use cases are some of the factors that are taken into consideration when analyzing the works reviewed in the literature.ABBREVIATIONS: IoT: Internet of Things; FL: Federated Learning; ZKP: Zero-Knowledge Proof; SMPC: Secure Multi-Party Computation; DP: Differential Privacy; DL: Deep Learning; EHR: Electronic Health Repository; AI: Artificial Intelligence; LSTM: Long Short-Term Memory; KPABE: Key-Policy Attribute-Based Encryption; GRU: Gated Recurrent Units; HABE: Hierarchical Attribute-Based Encryption; APoW: Adaptive Proof of Work; IoMT: Internet of Medical Things; RSU: Roadside Units; BFT: Byzantine Fault Tolerant; RP: Radial Point; GM-SSO: Genetically Modified Salp Swarm Optimization; SVM: Support Vector Machines; TP2SF: Trustworthy Privacy-Preserving Secured Framework; PCA: Principal Component Analysis; ePoW: Enhanced Proof of Work; XGBoost: Gradient Tree Boosting System; PSI: Privacy Set Intersection; WSN: Wireless Sensor Networks; PoT: Proof of Trust; CPPA: Conditional Privacy-Preserving Authentication; BTCPS: Conditional Privacy-Preserving Announcement Scheme; VANET: Vehicular Ad Hoc Network; OMLIDS-PBIoT: Optimal Machine Learning – Based Intrusion Detection System ForProtecting Privacy In Biomedical Internet Of Things; GEO: Golden Eagle Optimization; FS: Feature Selection; RVFL: Random Vector Functional Link Network; HBO: Heap-Based Optimizer; HPT: Hierarchical Purpose Trees; TS-PBAC: Triple Subject Purpose-Based Access Control; MCS: Mobile Cloud Services; IoHT: Internet Of Health Things; DQN: Deep Q-Network; IECDSA: An Intelligent Elliptic Curve Digital Signature Algorithm; IIoT: Industrial Internet of Things; DPoS: Delegated Proof of Stake; RDPoS: Reputation-Based Delegated Proof Of Stake; MC: Manage Contract; TIC: Token Issue Contract; RNN: Recurrent Neural Network; NTRU: Nth-Degree Truncated Polynomial Ring Units; PKI: Public Key Infrastructure; PTAS: Privacy-Preserving Thin-Client Authentication Scheme; ML: Machine Learning; DNN: Deep Neural Network; PPSF-BODL : Privacy-Preserving Secure Framework Using Blockchain; With Optimal Deep Learning; URC: User Register Contract; ML: Machine Learning

Himanshu Nandanwar, Rahul Katarya

Abstract Blockchain technology offers a secure solution for managing sensitive data with Artificial Intelligence, supply chain, cloud computing, and healthcare applications. Its key features, confidentiality, decentralization, security, and privacy, enhance healthcare systems, especially when integrated with Internet of Things (IoT) devices. This integration improves communication between healthcare systems and IoT devices, increasing security, privacy, and operational efficiency. However, traditional healthcare systems face challenges like phishing, identity theft, and masquerading attacks. We propose a blockchain-based decentralized application to mitigate these risks and generate, maintain, and validate healthcare medical certificates. The application enables secure communication between hospitals, patients, doctors, and IoT devices using smart contracts for confidentiality and authentication. Our architecture utilizes Non-Interactive Zero-Knowledge Proof to maintain data integrity and privacy. We further integrate Blockchain Data Storage and the Inter-Planetary File System to reduce storage costs and enhance security through Ethereum smart contracts. An Intrusion Detection System monitors IoT traffic to detect potential security threats. Performance analysis demonstrates that this solution addresses key security and privacy challenges, offering an efficient and scalable framework for healthcare data management.

Vinayak Musale, Poonam Bhosale, Sumegh Tharewal, Madhuri Rao · 6 authors

Mobile payment systems have transformed financial transactions with unprecedented ease and accessibility. But the explosion in their numbers has been met with increasing security threats and issues of privacy. This paper puts forward a new blockchain-based paradigm for mobile payment systems that prioritizes privacy but retains high-security standards. This design leverages the essential capabilities of blockchain technology like decentralization, immutability, and cryptographic protection. It incorporates advanced privacy-protecting techniques such as zero-knowledge proofs and homomorphic encryption. The system design intended here is to mitigate common vulnerabilities present in centralized systems, reduce the risk of data breaches, and provide users with more control over their financial data. By comparative analysis and simulations, we show that our privacy-oriented blockchain solution strongly improves transaction security, minimizes fraud, and maintains user anonymity without sacrificing system performance or compliance with regulations. This work is a contribution to the ongoing work on developing more secure and privacy-aware financial technologies in a rapidly digitalizing economy.

Yi-Jing Liu, Long Zhang, Xiaoqian Li, Hongyang Du · 7 authors

Federated learning (FL) is integral to advancing edge intelligence by enabling collaborative machine learning. In FL-empowered edge networks, computing nodes first train local models and then send them to an or multiple aggregation node(s) for global model collaboration. However, the trustworthiness of both local and global models in conventional FL frameworks is compromised due to inadequate model security and transparency. Distributed ledger technique (DLT) can address this issue by leveraging multi-nodes trust capabilities to support distributed consensus. However, model training and consensus performance of DLT may significantly degrade due to instability and resource constraints of edge networks. Sharding technique provides an effective approach by dividing the ledger into smaller and manageable shards. In this paper, to improve model training and consensus performance, we propose a trusted FL framework by incorporating sharding DLT into FL frameworks. We construct a theoretical model to investigate the relationship between model training performance, consensus efficiency, and capacity of edge nodes regarding storage, computing and communications. Based on the theoretical model, we propose a trusted clustering scheme to aggregate local models. Numerical results show that our proposed scheme significantly improves network throughput for transmitting models while guaranteeing model learning performance in comparison with some classical baselines.

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.

Shamim Akhtar, Muhammad Taimoor, Ghulam Fatima, Hurma Islam

This research explores the transformative role of blockchain technology in ensuring secure and trustworthy digital transactions. With the increasing reliance on digital platforms across industries such as finance, healthcare, and supply chains, blockchain has emerged as a solution to the challenges posed by traditional centralized systems, including data breaches, fraud, and lack of transparency. The study investigates blockchain's decentralized structure, cryptographic security features, consensus mechanisms, and smart contracts to evaluate how it enhances data integrity and trust in digital transactions. A qualitative approach was employed, utilizing case studies and a comprehensive review of existing literature. The results show that blockchain’s decentralization significantly reduces single points of failure, while its consensus mechanisms and smart contracts increase trust and automate transactions. However, challenges such as scalability, energy consumption, and regulatory concerns remain. The research highlights blockchain’s potential for transforming digital transactions but calls for further innovation to address these issues. The findings suggest that blockchain has the capacity to revolutionize secure transactions across various sectors but requires continued development to achieve widespread adoption and scalability.

Dongyu Cao, Hao Yin, Bixin Li

No abstract is available for this record.

Haochen Sun, Xi He

Although differential privacy (DP) is widely regarded as the de facto standard for data privacy, its implementation remains vulnerable to unfaithful execution by servers, particularly in distributed settings. In such cases, servers may sample noise from incorrect distributions or generate correlated noise while appearing to follow established protocols. This work addresses these malicious behaviours in a distributed client-server-verifier setup, under Verifiable Distributed Differential Privacy (VDDP), a novel framework for the verifiable execution of distributed DP mechanisms. We systematically capture end-to-end security and privacy guarantees against potentially colluding adversarial behaviours of clients, servers, and verifiers by characterizing the connections and distinctions between VDDP and zero-knowledge proofs (ZKPs). We develop three novel and efficient instantiations of VDDP: (1) the Verifiable Distributed Discrete Laplace Mechanism (VDDLM), which achieves up to a 400,000x improvement in proof generation efficiency with only 0.1--0.2x error compared with the previous state-of-the-art verifiable differentially private mechanism and includes a tight privacy analysis that accounts for all additional privacy losses due to numerical imprecisions, applicable to other secure computation protocols for DP mechanisms based on cryptography; (2) the Verifiable Distributed Discrete Gaussian Mechanism (VDDGM), an extension of VDDLM that incurs limited overhead in real-world applications; and (3) an improved solution to Verifiable Randomized Response (VRR) under local DP, as a special case of VDDP, achieving up to a 5,000x reduction in communication costs and verifier overhead.

Ferhat Özgür Çatak, Chunming Rong, Øyvind Meinich-Bache, Sara Brunner · 5 authors

This study introduces a cutting-edge architecture developed for the NewbornTime project, which uses advanced AI to analyze video data at birth and during newborn resuscitation, with the aim of improving newborn care. The proposed architecture addresses the crucial issues of patient consent, data security, and investing trust in healthcare by integrating Ethereum blockchain with cloud computing. Our blockchain-based consent application simplifies patient consent's secure and transparent management. We explain the smart contract mechanisms and privacy measures employed, ensuring data protection while permitting controlled data sharing among authorized parties. This work demonstrates the potential of combining blockchain and cloud technologies in healthcare, emphasizing their role in maintaining data integrity, with implications for computer science and healthcare innovation.

Saad Alahmari, Amal Alshardan, Fahd N. Al‐Wesabi, Shaymaa E. Sorour · 8 authors

As healthcare services have become increasingly digitized, Electronic Health Records (EHRs) have become widely adopted, providing seamless data exchange among providers. Conventional EHRs, however, are extremely vulnerable to cyber threats because patients' sensitive data is centralized and transmitted electronically. The paper proposes a decentralized, privacy-preserving framework for managing EHRs on blockchains in order to address these security and privacy concerns. Using cryptographic techniques, such as homomorphic encryption and zero-knowledge proofs, the proposed system enhances security and ensures data integrity. Additionally, the model facilitates scalable, efficient, and secure access to patient records through the integration of cloud-based storage and blockchain. Using smart contracts, we also ensure compliance with healthcare regulations by regulating access control and authentication. As a result of performance evaluations, the proposed approach is demonstrated to be feasible, and the advantages it offers in terms of security, privacy, and efficiency are highlighted.

Yanghe Pan, Zhou Su, Yuntao Wang, Han Liu · 6 authors

Federated learning (FL) model marketplaces require qualified workers to collaboratively train customized models. However, recruiting optimal workers on a limited budget in non-independent and identically distributed (non-IID) data settings remains a fundamental issue. Moreover, inadequate quality verification exposes the marketplace to spoofing and poisoning attacks, while verifying data and model quality without accessing local storage remains a significant dilemma. To bridge the research gap, this paper proposes a knowledge-aware model customization scheme in FL model marketplaces, to facilitate zero-trust worker recruitment and verification while ensuring privacy preservation. Specifically, (i) we design a knowledge-aware quality evaluation mechanism by leveraging the knowledge of workers, i.e., soft-label predictions of their local models on a privacy-free reference dataset (provided by the customer), to assess their data quality in a privacy-preserving manner. (ii) We formulate the optimal worker recruitment problem under budget constraints as an NP-hard integer programming problem and design a dynamic programming-based optimal worker recruitment algorithm with budget feasibility and computational efficiency. (iii) We devise a two-stage zero-trust quality verification mechanism by utilizing zero-knowledge proof (ZKP) to exclude distrustful workers, thereby preventing spoofing and poisoning attacks. Extensive experimental results demonstrate that the proposed scheme enhances model customization performance by up to 34.3% on label-skewed non-IID data and 36.2% on feature-skewed non-IID data compared with existing representatives.

Mohammad M Maheri, Hamed Haddadi, Alex Davidson

Verification of the integrity of deep learning inference is crucial for understanding whether a model is being applied correctly. However, such verification typically requires access to model weights and (potentially sensitive or private) training data. So-called Zero-knowledge Succinct Non-Interactive Arguments of Knowledge (ZK-SNARKs) would appear to provide the capability to verify model inference without access to such sensitive data. However, applying ZK-SNARKs to modern neural networks, such as transformers and large vision models, introduces significant computational overhead. We present TeleSparse, a ZK-friendly post-processing mechanisms to produce practical solutions to this problem. TeleSparse tackles two fundamental challenges inherent in applying ZK-SNARKs to modern neural networks: (1) Reducing circuit constraints: Over-parameterized models result in numerous constraints for ZK-SNARK verification, driving up memory and proof generation costs. We address this by applying sparsification to neural network models, enhancing proof efficiency without compromising accuracy or security. (2) Minimizing the size of lookup tables required for non-linear functions, by optimizing activation ranges through neural teleportation, a novel adaptation for narrowing activation functions' range. TeleSparse reduces prover memory usage by 67% and proof generation time by 46% on the same model, with an accuracy trade-off of approximately 1%. We implement our framework using the Halo2 proving system and demonstrate its effectiveness across multiple architectures (Vision-transformer, ResNet, MobileNet) and datasets (ImageNet,CIFAR-10,CIFAR-100). This work opens new directions for ZK-friendly model design, moving toward scalable, resource-efficient verifiable deep learning.

Ravi Mishra, Rushikesh Bankar

The integration of machine learning (ML) in healthcare has unlocked transformative potential in disease prediction, personalized treatment, medical imaging, remote patient monitoring, and genomic data analysis. However, the sensitive nature of medical data introduces critical concerns regarding patient privacy, data security, and regulatory compliance. This chapter presents a comprehensive overview of privacy-preserving machine learning approaches tailored for healthcare applications, with a focus on technical frameworks, real-time implementations, and regulatory alignment. It explores the use of advanced techniques such as federated learning, differential privacy, homomorphic encryption, and zero-knowledge proofs to safeguard patient information while maintaining model utility. The chapter also addresses domain-specific challenges in processing real-time health data streams and implementing privacy-aware algorithms in resource-constrained environments. By bridging the gap between technical innovation and clinical applicability, this work emphasizes the importance of secure, scalable, and ethically aligned ML solutions in modern healthcare ecosystems. The discussion was contextualized within current legal frameworks and highlights future directions for research and implementation to ensure trust, transparency, and resilience in data-driven medical systems.

N. S. Swapna, A. Muralidhar, Kambala Madhu Latha, M. Archana · 9 authors

Neural Network design by a group of clients (each is a person who owns the data) where the data remains private. FL is vulnerable to adversarial attacks, data poisoning, and Byzantine faults, which are threats destroying the integrity as well as the security of the trained model. In order to deal with the challenges above, we propose a new framework, namely FL-GAN-TrustDP, for security enhanced FL using Generative Adversarial Networks (GANs) for adversarial defence, blockchain based hierarchical trust evaluation and adaptive differential privacy. Optimizing the privacy-utility tradeoff based on client trust scores, the adaptive privacy mechanism is a mechanism. GAN based adversarial filtering helps in detecting adversarial updates and thus preventing it, and the trust mechanism backed by blockchain dynamically penalizes the malicious clients. Experimental results show that FL-GAN-TrustDP significantly outperforms baseline FL models (in terms of higher model accuracy, lower adversarial success rates, lower false alarms and faster convergence speed) compared to FedAvg, FedSGD, FedDP, FedBlockchain. In particular, the adversarial success rate on adversarial data seems to decrease significantly from 60% to below 30%, and the notice is more precise, recall, and F1 score than previous work for safeguarding FL. This proposed framework promotes security, privacy, and robustness for FL applications and thus can be a secure federated learning solution in IoT and edge computing environments.

Sathwik Narkedimilli, P. Pravisha, Amballa Venkata Sriram, Satvik Raghav · 5 authors

Federated Learning (FL) offers a distributed approach to machine learning that preserves data privacy by avoiding the exchange of sensitive IoT sensor information. This paper introduces a novel IoT framework that integrates advanced security tools to tackle key privacy and security challenges. It employs Decentralized Attribute-Based Encryption (DABE) for decentralized authentication and data encryption, Homomorphic Encryption (HE) for secure computations on encrypted data, Secure Multi-Party Computation (SMPC) for collaborative processing, and Blockchain for distributed ledger management and transparent communication. In this system, IoT devices encrypt data locally with DABE, while initial model training occurs on cloud servers within an immutable blockchain network that supports peer-to-peer authentication. Encrypted model weights are then transferred to the fog layer via HE and aggregated using SMPC, after which the FL server updates and distributes the global model to the IoT devices. This innovative framework effectively addresses the challenges of secure decentralized learning, enabling privacy-preserving, efficient, and secure federated learning for IoT applications and real-time analytics.

Ratun Rahman

Federated Learning (FL) has emerged as a transformative paradigm in the field of distributed machine learning, enabling multiple clients such as mobile devices, edge nodes, or organizations to collaboratively train a shared global model without the need to centralize sensitive data. This decentralized approach addresses growing concerns around data privacy, security, and regulatory compliance, making it particularly attractive in domains such as healthcare, finance, and smart IoT systems. This survey provides a concise yet comprehensive overview of Federated Learning, beginning with its core architecture and communication protocol. We discuss the standard FL lifecycle, including local training, model aggregation, and global updates. A particular emphasis is placed on key technical challenges such as handling non-IID (non-independent and identically distributed) data, mitigating system and hardware heterogeneity, reducing communication overhead, and ensuring privacy through mechanisms like differential privacy and secure aggregation. Furthermore, we examine emerging trends in FL research, including personalized FL, cross-device versus cross-silo settings, and integration with other paradigms such as reinforcement learning and quantum computing. We also highlight real-world applications and summarize benchmark datasets and evaluation metrics commonly used in FL research. Finally, we outline open research problems and future directions to guide the development of scalable, efficient, and trustworthy FL systems.

S. M. Sakthivel, N. Suresh Kumar, R. Kanniga Devi

The Border Gateway Protocol (BGP) experiences multiple security threats during inter-domain routing such as prefix hijacking and route leaks and man-in-the-middle attacks. Resource Public Key Infrastructure (RPKI) and BGPsec along with other security solutions authenticate networks better but lack protection of network privacy and exhibit weaknesses due to concentration of authority. This paper introduces an integrated ZKP-based Route Verification Framework which uses blockchain technology to establish tamper-resistant privacy-preserving route validation. The framework includes five fundamental elements that provide ZKP proof generation for route credentials and blockchain-based proof storage and automated proof verification with BGP extension and off-chain IPFS-based proof management systems. The system architecture uses zk-SNARKs for cryptographic verifications while it relies on Hyperledger Fabric for decentralized proof validation. The proposed solution achieved superior routing security because it maintains both efficient storage scalability and minimal computational overhead according to performance testing results. The system results show that this framework provides adequate capabilities for actual Internet Service Provider deployments which support decentralized routing across domains while maintaining privacy protection.

Mayur Patel, Aditya Vishwakarma, Mohammad Kaif, Shahan Ali

Abstract: Online blockchain-based certificate generation and validation represent a crucial advancement in enhancing transparency, security, and efficiency within government operations. This system enables government organizations to securely issue, verify, and manage certificates, ensuring the integrity of essential documents such as birth certificates, educational diplomas, business licenses, and other critical records. The integration of blockchain technology into certificate management systems can significantly streamline government services while safeguarding against fraudulent activities, document tampering, and administrative errors.In recent years, however, blockchain technology has emerged as a promising solution to address these issues, offering a decentralized, tamper-proof system for the generation and validation of certificates. Blockchain, which is essentially a distributed ledger, stores data across a network of nodes, making it virtually immutable and highly resistant to alterations. Each record or transaction on the blockchain is cryptographically secured, ensuring that once a certificate is issued and recorded, it cannot be modified or deleted without detection

Sagnik Datta, Suyel Namasudra

ABSTRACT Blockchain technology is gaining importance in different sectors like healthcare, finance, agriculture, and many more. The important capabilities of blockchain like decentralization, immutability, consensus mechanism, etc. provide security, privacy, transparency, accountability, and many other benefits. On the other hand, Mobile Edge Computing (MEC) is a distributed framework that provides cloud computing capabilities to mobile devices. The existing studies combining blockchain technology and MEC often do not consider the delay and energy consumption for data offloading. In this paper, a blockchain‐based scheme has been proposed for sharing Internet of Medical Things (IoMT) data between a patient and a doctor, which offloads tasks to the MEC server to achieve energy efficiency. In the proposed scheme, the Non‐Orthogonal Multiple Access (NOMA) protocol is used to share a channel among several users. Here, NOMA offers some advantages in the system like low cost, latency, and power consumption. In the proposed scheme, the energy consumption is optimized based on the task delegation decision and resource distribution in the MEC server. Additionally, operations of the blockchain network are automated using various smart contracts. The efficiency of the proposed scheme is analyzed in terms of energy consumption, average transmission rate, and offloading delay in processing healthcare data. The experimental results demonstrate that the proposed model enhances energy efficiency and optimizes performance compared to the state‐of‐the‐art offloading schemes.

Ruonan Chen, Ye Dong, Yizhong Liu, Tingyu Fan · 8 authors

Federated Learning (FL) is a distributed machine learning paradigm that allows multiple clients to train models collaboratively without sharing local data. Numerous works have explored security and privacy protection in FL, as well as its integration with blockchain technology. However, existing FL works still face critical issues. i) It is difficult to achieving poisoning robustness and data privacy while ensuring high model accuracy. Malicious clients can launch poisoning attacks that degrade the global model. Besides, aggregators can infer private data from the gradients, causing privacy leakages. Existing privacy-preserving poisoning defense FL solutions suffer from decreased model accuracy and high computational overhead. ii) Blockchain-assisted FL records iterative gradient updates on-chain to prevent model tampering, yet existing schemes are not compatible with practical blockchains and incur high costs for maintaining the gradients on-chain. Besides, incentives are overlooked, where unfair reward distribution hinders the sustainable development of the FL community. In this work, we propose FLock, a robust and privacy-preserving FL scheme based on practical blockchain state channels. First, we propose a lightweight secure Multi-party Computation (MPC)-friendly robust aggregation method through quantization, median, and Hamming distance, which could resist poisoning attacks against up to <50% malicious clients. Besides, we propose communication-efficient Shamir's secret sharing-based MPC protocols to protect data privacy with high model accuracy. Second, we utilize blockchain off-chain state channels to achieve immutable model records and incentive distribution. FLock achieves cost-effective compatibility with practical cryptocurrency platforms, e.g. Ethereum, along with fair incentives, by merging the secure aggregation into a multi-party state channel. In addition, a pipelined Byzantine Fault-Tolerant (BFT) consensus is integrated where each aggregator can reconstruct the final aggregated results. Lastly, we implement FLock and the evaluation results demonstrate that FLock enhances robustness and privacy, while maintaining efficiency and high model accuracy. Even with 25 aggregators and 100 clients, FLock can complete one secure aggregation for ResNet in 2 minutes over a WAN. FLock successfully implements secure aggregation with such a large number of aggregators, thereby enhancing the fault tolerance of the aggregation.

Daniel Commey, Sena Hounsinou, Garth V. Crosby

The growth of IoT in healthcare generates massive sensitive data. This necessitates a secure and privacy-preserving distributed network to transport and process the data. Federated learning (FL) offers privacy-preserving model training, while blockchain ensures data integrity through transparency and immutability. Yet, quantum computing threatens cryptographic schemes like ECDSA, endangering long-term data confidentiality. This paper integrates post-quantum cryptography (PQC) with blockchain-based FL for healthcare analytics. We evaluate three signature-based PQC algorithms–Falcon, Dilithium (ML-DSA-65), and SPHINCS+ (SPHINCS+-SHA2-128s)–to assess their impact on blockchain transaction costs and latency. Benchmarks on a local Ethereum testnet show that lattice-based schemes, particularly ML-DSA-65, achieve verification under 10 ms with acceptable gas costs. Our findings indicate that smart contract signature verification is the primary gas consumer, offering guidelines for deploying quantum-resistant FL systems. These findings justify and potentially create a foundation for building complete systems that integrate PQC into Blockchain-based FL systems.

Haotian Yin, Jie Zhang, Wanxin Li, Yuji Dong · 6 authors

No abstract is available for this record.