Gabriel Chukwunonso Amaizu, Akshita Maradapu Vera Venkata Sai, Sanjay Bhardwaj, DongâSeong Kim ¡ 6 authors
The increasing prevalence of cancer necessitates advanced methodologies for early detection and diagnosis. Early intervention is crucial for improving patient outcomes and reducing the overall burden on healthcare systems. Traditional centralized methods of medical image analysis pose significant risks to patient privacy and data security, as they require the aggregation of sensitive information in a single location. Furthermore, these methods often suffer from limitations related to data diversity and scalability, hindering the development of universally robust diagnostic models. Recent advancements in machine learning, particularly deep learning, have shown promise in enhancing medical image analysis. However, the need to access large and diverse datasets for training these models introduces challenges in maintaining patient confidentiality and adhering to strict data protection regulations. This paper introduces FedViTBloc, a secure and privacy-enhanced framework for medical image analysis utilizing Federated Learning (FL) combined with Vision Transformers (ViT) and blockchain technology. The proposed system ensures patient data privacy and security through fully homomorphic encryption and differential privacy techniques. By employing a decentralized FL approach, multiple medical institutions can collaboratively train a robust deep-learning model without sharing raw data. Blockchain integration further enhances the security and trustworthiness of the FL process by managing client registration and ensuring secure onboarding of participants. Experimental results demonstrate the effectiveness of FedViTBloc in medical image analysis while maintaining stringent privacy standards, achieving 67% accuracy and reducing loss below 2 across 10 clients, ensuring scalability and robustness.
Open access
Artificial Intelligence in Healthcare and Education
Large language models (LLMs) are increasingly utilized in domains such as finance, healthcare, and interpersonal relationships to provide advice tailored to user traits and contexts. However, this personalization often relies on sensitive data, raising critical privacy concerns and necessitating data minimization. To address these challenges, we propose a framework that integrates zero-knowledge proof (ZKP) technology, specifically zkVM, with LLM-based chatbots. This integration enables privacy-preserving data sharing by verifying user traits without disclosing sensitive information. Our research introduces both an architecture and a prompting strategy for this approach. Through empirical evaluation, we clarify the current constraints and performance limitations of both zkVM and the proposed prompting strategy, thereby demonstrating their practical feasibility in real-world scenarios.
The medical industry has made significant advancements in recent years. However, the lack of accountability in medical management has resulted in systemic deficiencies, which have adversely affected patient trust and contributed to an increase in medical disputes. As a result, there is a growing emphasis on managing the quality of medical services, particularly in enhancing patient experience. To address these challenges, we propose a new system for evaluating health services. This system will allow patients to anonymously rate the services they receive while also providing doctors the opportunity to appeal specific reviews. The hospital handles the evaluations and appeals through the management of the cloud platform. We propose a new scheme to assist the work of the platform, which is a lattice-based group signature with verifier-local revocation (VLR-GS). Most of the work on VLR-GS has focused on the random oracle model (ROM) or using non-interactive zero-knowledge proofs (NIZKs). Our construction is anonymous and traceable in the standard model under the hardness of the learning with errors problem and short integer solution problem. Furthermore, theoretically analyzing it has practical significance in both security and efficiency. In conclusion, the proposed scheme establishes a secure and privacy-oriented platform for an anonymous medical service evaluation system, with the goal of fostering patient trust and improving hospital service quality within the healthcare sector.
Federated Learning (FL), which permits decentralized model training without sharing raw data, guarantees âadherence to privacy laws like GDPR and HIPAA. This study offers a thorough analysis of FL with an âemphasis on its exceptional capacity to strike a balance between data value and privacy in industries âincluding healthcare, the Internet of Things, and finance. In contrast to previous evaluations, this study âexplores sophisticated privacy-preserving techniques, such as differential privacy and homomorphic âencryption, and assesses how well they work to handle issues like adversarial threats, non-IID data âdistributions, and communication overhead. The study also discusses the practical uses of optimization âtechniques like Federated Proximal (FedProx) and Federated Averaging (FedAvg). This paper provides âpractical insights and future approaches to promote the use of FL in privacy-sensitive AI applications by âcomparing and contrasting current methods and pointing out research gaps. FL is positioned as a ârevolutionary method for privacy-conscious machine learning because to this fresh viewpoint. This update highlights the paper's distinctive features that set it apart from prior reviews, including the âthorough examination of privacy mechanisms, assessment of optimization techniques, and identification âof research needsâ.
With the further expansion of 5G networks, a main priority continues to shift towards secure and efficient protocols for data transmission. Traditional 5G security mechanisms, such as 3GPP AKA protocols, have limitations in scalability, latency, and resilience against cyber threats, making them quite unsuitable for complex high-density 5G environments. This study proposes a Secure Blockchain-based Data Transmission Protocol (SBDTP) with the decentralized and tamper-resistant feature of blockchain, combined with a hybrid consensus mechanism driven by Proof of Stake (PoS) or Practical Byzantine Fault Tolerance (PBFT). In this respect, this study contributes to state-of-the-art research efforts in the field of enhancing data integrity, authentication, and confidentiality with reduced latency and energy consumption in 5G applications. Extensive simulations showed that SBDTP outperformed previous solutions by a large margin. This protocol reduces latency to 50-80 ms, increases throughput to 900 pps, allows up to 1000 nodes without performance degradation, and reduces energy consumption to 0.8 J per node. It also maintains a very close-to-perfection data integrity check rate of ~100% and a very minimal privacy loss rate of less than 1%, showing strong security that could serve well for real-time 5G applications such as IoT networks, autonomous vehicles, and smart cities. These results show that SBDTP offers an efficient and secure solution for data transmission over 5G networks, outperforming traditional and blockchain-based methods while fulfilling the tight requirements posed by next-generation networks. In the future, the protocol should be optimized for scalability, including further advanced privacy techniques to widen its adaptability to diverse 5G applications.
The proliferation of Internet of Things (IoT) devices in smart environments has created unprecedented challenges in identity management and security. Traditional centralized identity management systems face scalability, privacy, and single-point-of-failure issues when applied to IoT ecosystems. This paper presents a novel blockchain-based framework for decentralized identity management in smart IoT environments. Our proposed framework leverages blockchain technology's immutable ledger, smart contracts, and cryptographic mechanisms to provide secure, scalable, and privacy-preserving identity management for IoT devices. The framework incorporates a multi-layered security architecture that includes device authentication, access control, and identity verification mechanisms. Experimental results demonstrate that our approach achieves 99.7% authentication accuracy with reduced latency compared to traditional centralized systems. The framework also provides enhanced privacy protection through zero-knowledge proofs and selective disclosure mechanisms. This research contributes to the advancement of secure IoT identity management and provides a foundation for future developments in decentralized IoT security
Nadeem Yaqub, Jianbiao Zhang, Muhammad Irfan Khalid, Weiru Wang ¡ 7 authors
Electronic health record transmission and storage involve sensitive information, requiring robust security measures to ensure access is limited to authorized personnel. In the existing state of the art, there is a growing need for efficient access control approaches for the secure accessibility of patient health data by sustainable electronic health records. Locking medical data in a healthcare center forms information isolation; thus, setting up healthcare data exchange platforms is a driving force behind electronic healthcare centers. The healthcare entities access rights like subject, controller, and requester are defined and regulated by access control policies as defined by the General Data Protection Regulation (GDPR). In this work, we have introduced a blend of policy-based access control (PBAC) system backed by blockchain technology, where smart contracts govern the intrinsic part of security and privacy. As a result, any Subject can know at any time who currently has the right to access his data. The PBAC grants access to electronic health records based on predefined policies. Our proposed PBAC approach employs policies in which the subject, controller, and requester can grant access, revoke access, and check logs and actions made in a particular healthcare system. Smart contracts dynamically enforce access control policies and manage access permissions, ensuring that sensitive data is available only to authorized users. Delineating the proposed access control system and comparing it to other systems demonstrates that our approach is more adaptable to various healthcare data protection scenarios where there is a need to share sensitive data simultaneously and a robust need to safeguard the rights of the involved entities.
Patient privacy data security is a pivotal area of research within the burgeoning field of smart healthcare. This study proposes an innovative hybrid blockchain-based framework for the secure sharing of electronic medical record (EMR) data. Unlike traditional privacy protection schemes, our approach employs a novel tripartite blockchain architecture that segregates healthcare data across distinct blockchains for patients and healthcare providers while introducing a separate social blockchain to enable privacy-preserving data sharing with authorized external entities. This structure enhances both security and transparency while fostering collaborative efforts across different stakeholders. To address the inherent complexity of managing multiple blockchains, a unique cross-chain signature algorithm is introduced, based on the Boneh-Lynn-Shacham (BLS) signature aggregation technique. This algorithm not only streamlines the signature process across chains but also strengthens system security and optimizes storage efficiency, addressing a key challenge in multi-chain systems. Additionally, our external sharing algorithm resolves the prevalent issue of medical data silos by facilitating better data categorization and enabling selective, secure external sharing through the social blockchain. Security analyses and experimental results demonstrate that the proposed scheme offers superior security, storage optimization, and flexibility compared to existing solutions, making it a robust choice for safeguarding patient data in smart healthcare environments.
The growing number of consumer Internet of Things (IoT) gadgets, including smart homes, fitness trackers, connected appliances, and home security systems, is transforming the way we live our daily lives. This has led to the emergence of a collaborative cloud-edge paradigm to leverage resources and services near the end-user, thereby providing prompt response to delay-sensitive real-time applications. Nevertheless, the tremendous amount of data generated by various IoT devices and sent over the network is always an open security challenge. The introduction of Federated Learning (FL) addresses the security and data privacy shortcomings of traditional centralized machine learning. Despite FLâs use for data privacy, it must overcome a number of significant challenges, such as privacy concerns, communication overhead, stragglers, and heterogeneity. To solve these challenges, this paper proposes a novel technique for enhancing security in IoT-enabled edge cloud computing networks, utilizing blockchain-driven FL and Gaussian Bayesian transfer convolutional neural network architectures for data analysis. Blockchain-driven FL ensures the security and privacy of consumer IoT applications. In comparison to state-of-the-art works, the experimental results achieved throughput of up to 89%, latency of 71%, training accuracy of 91%, validation accuracy of 96%, and network security of 92%.
Abstract Authentication and access control for Cyber-Physical Systems (CPSs) are pivotal for protecting systems and their users from problems related to harmful actions and the malicious use of retrieved data. In some situations, making access decisions requires using user information, thereby challenging their privacy. Attribute-based access control (ABAC) supports dynamic and context-aware access decisions that are attractive in cyber-physical system environments. However, privacy preservation for access decisions is an open issue for authorization and is not supported by existing ABAC models. For example, if access decisions need to be made based on private attribute values such as health data, the corresponding access control policies need to be revealed. This paper reviews the ABAC, homomorphic encryption (HE), and zero-knowledge proof (ZKP) approaches, confirming the gap in privacy preservation in ABAC. Based on this observation, we further present the application of a new ZKP-based protocol in which ABAC allows for the privacy-preserving evaluation of attributes. This protocol is implemented and evaluated in terms of its performance and security. The evaluation demonstrates that there is a possibility for privacy-preserving ABAC, which may benefit the use of CPS, e.g., in underground and open-pit mines.
Ahmed M. Tawfik, Ayman Al-Ahwal, Adly S. Tag Eldien, Hala H. Zayed
Abstract Advances in blockchain technology offer a decentralized ledger with transformative potential for healthcare data management, facilitating secure transactions and transparent record-keeping. Nevertheless, the sensitive nature of patient data requires enhanced privacy measures. This paper introduces a comprehensive framework enabling researchers to conduct collaborative statistical analysis on health records while preserving privacy and ensuring security. Statistics are invaluable across various disciplines, guiding consequential decisions based on such analysis. The framework integrates privacy-preserving techniques, including secret-sharing, secure multiparty computation (SMPC), and homomorphic encryption, within a blockchain-based healthcare ecosystem. Patient data is divided using secret-sharing, enabling controlled access. Furthermore, SMPC allows secure data aggregation without revealing individual records, while homomorphic encryption supports computation on encrypted data within smart contracts. Through a series of controlled experiments, we assess the frameworkâs effectiveness in maintaining data privacy, facilitating secure collaboration, and conducting statistical data analysis. The results demonstrate successful preservation of data privacy and secure analysis on a permissioned blockchain using the Hyperledger Fabric platform. Our framework showcases efficient performance while effectively utilizing system resources. This research contributes to the evolution of secure and privacy-conscious healthcare data analysis, paving the way for practical applications and future advancements.
Federated Learning (FL) has emerged as a promising paradigm that addresses the delicate balance between data-intensive model development and the preservation of user privacy. Unlike the conventional approach of aggregating large volumes of raw data in a single data center, FL conducts local training on various devices or institutional serversâsometimes referred to as âclientsââand only exchanges model parameters or gradients with a central entity. By design, this decentralized framework keeps personal or proprietary data within the confines of the originating device or organization, significantly reducing the chances of exposing sensitive information. A primary motivation for FL is the ever-increasing concern over privacy violations and compliance with stringent regulations such as the General Data Protection Regulation (GDPR) and the California Consumer Privacy Act (CCPA). As global data protection standards continue to evolve, FL offers a compelling solution by minimizing direct data sharing and thereby mitigating the risk of large-scale breaches. Beyond privacy considerations, FL holds practical appeal in many real-world scenarios, including healthcare, finance, the Internet of Things (IoT), and various consumer-focused applications. These sectors routinely handle confidential or regulated dataâmedical records, bank transactions, or user habitsâwhere a centralized data repository poses both security and compliance hazards. Nevertheless, FL also introduces its own set of challenges. Heterogeneous data distributions across clients can lead to biases and uneven training dynamics. Additionally, new threat vectorsâsuch as model poisoning and inference attacksâhave surfaced within decentralized training environments, prompting research into robust security strategies. Furthermore, practical implementation demands careful planning around communication overhead, computational capacity of clients, and the trade-offs that arise when adding privacy guarantees like Differential Privacy or Secure Multi-Party Computation. This paper explores the theoretical underpinnings of Federated Learning, reviews cutting-edge privacy-preserving techniques, examines potential security pitfalls, and presents real-world applications augmented by case studies. We also discuss performance evaluation methods crucial for determining FLâs viability and highlight upcoming research directions that can shape a secure, efficient, and privacy-centered AI ecosystem.
As an emerging paradigm in digital identity, Decentralized Identity (DID) appears advantages over traditional identity management methods in a variety of aspects, e.g., enhancing user-centric online services and ensuring complete user autonomy and control. Verifiable Credential (VC) techniques are used to facilitate decentralized DID-based access control across multiple entities. However, existing DID schemes generally rely on a distributed public key infrastructure that also causes challenges, such as context information deduction, key exposure, and issuer data leakage. To address the issues above, this paper proposes a issuer-hiding and privacy-preserving DID multi-party authentication model with a signature-less VC scheme, named SLVC-DIDA, for the first time. Our proposed scheme avoids the dependence on signing keys by employing hashing and issuer membership proofs, which supports universal zero-knowledge multi-party DID authentications, eliminating additional technical integrations. We adopt a novel zero-knowledge circuit to maintain the anonymity of the issuer set, thereby enabling public verification while safeguarding the privacy of identity attributes via a Merkle tree-based VC list. Furthermore, by eliminating reliance on a Public Key Infrastructure (PKI), SLVC-DIDA enables decentralized and self-sovereign DID authentication. Our experiments further evaluate the effectiveness and practicality of SLVC-DIDA.
Shoubai Nie, Jingjing Ren, Rui Wu, Pengchong Han ¡ 6 authors
Within the framework of 6G networks, the rapid proliferation of Internet of Things (IoT) devices, coupled with their decentralized and heterogeneous characteristics, presents substantial security challenges. Conventional centralized systems face significant challenges in effectively managing the diverse range of IoT devices, and they are inadequate in addressing the requirements for reduced latency and the efficient processing and analysis of large-scale data. To tackle these challenges, this paper introduces a zero-trust access control framework that integrates blockchain technology with inner-product encryption. By using smart contracts for automated access control, a reputation-based trust model for decentralized identity management, and inner-product encryption for fine-grained access control, the framework ensures data security and efficiency. Firstly, smart contracts are employed to automate access control, and software-defined boundaries are defined for different application domains. Secondly, through a trust model based on a consensus algorithm of node reputation values and a registration-based inner-product encryption algorithm supporting fine-grained access control, zero-trust self-sovereign enhanced identity management in the 6G environment of the Internet of Things is achieved. Furthermore, the use of multiple auxiliary chains for storing data across different application domains not only mitigates the risks associated with data expansion but also achieves micro-segmentation, thereby enhancing the efficiency of access control. Finally, empirical evidence demonstrates that, compared with the traditional methods, this paper's scheme improves the encryption efficiency by 14%, reduces the data access latency by 18%, and significantly improves the throughput. This mechanism ensures data security while maintaining system efficiency in environments with large-scale data interactions.
Yang Liu, Ru Huo, Ningjie Gao, Cheng Chi ¡ 5 authors
In order to address the challenges encountered in the current Industrial Internet of Things scenarios, such as single points of failure, difficulties in ensuring data privacy and integrity, and a lack of access control, a blockchain-based data security exchange architecture was proposed. To ensure the privacy of industrial data, a data exchange process based on public key encryption and keyword search was introduced. Industrial data is encrypted multiple times and uploaded to the blockchain network. Users retrieve ciphertext from the cloud server after obtaining the key through the blockchain and then decrypt it. To achieve flexible access control, a zero-knowledge proof-based access control mechanism was proposed, utilizing Pedersen commitments and zero-knowledge proofs for access permission issuance, validation, and revocation. Additionally, various forms of smart contracts were proposed for secure data exchange, user authentication, access authorization, and data integrity verification. Finally, a system prototype was built and experimental results confirmed the superiority of the proposed approach.
Ilia Shumailov, Daniel Ramage, Sarah Meiklejohn, Peter Kairouz ¡ 7 authors
We often interact with untrusted parties. Prioritization of privacy can limit the effectiveness of these interactions, as achieving certain goals necessitates sharing private data. Traditionally, addressing this challenge has involved either seeking trusted intermediaries or constructing cryptographic protocols that restrict how much data is revealed, such as multi-party computations or zero-knowledge proofs. While significant advances have been made in scaling cryptographic approaches, they remain limited in terms of the size and complexity of applications they can be used for. In this paper, we argue that capable machine learning models can fulfill the role of a trusted third party, thus enabling secure computations for applications that were previously infeasible. In particular, we describe Trusted Capable Model Environments (TCMEs) as an alternative approach for scaling secure computation, where capable machine learning model(s) interact under input/output constraints, with explicit information flow control and explicit statelessness. This approach aims to achieve a balance between privacy and computational efficiency, enabling private inference where classical cryptographic solutions are currently infeasible. We describe a number of use cases that are enabled by TCME, and show that even some simple classic cryptographic problems can already be solved with TCME. Finally, we outline current limitations and discuss the path forward in implementing them.
Federated Learning (FL) is a distributed machine learning paradigm that enables collaborative model training across decentralized devices while preserving data privacy. It addresses critical challenges in privacy, scalability, and data ownership, making it a promising approach for applications in healthcare, IoT, and finance. However, practical implementation of FL faces several efficiency bottlenecks, including communication overhead, system and data heterogeneity, and security vulnerabilities. This paper provides a comprehensive survey of state-of-the-art techniques aimed at enhancing the efficiency of FL. Key methods such as model compression, including pruning, quantization, and tensor decomposition, are explored to address communication constraints. Strategies to mitigate data and system heterogeneity, including personalized FL and resource-aware training, are discussed alongside advancements in privacy-preserving mechanisms like differential privacy and secure aggregation. We also examine scalability solutions, including hierarchical and decentralized FL, to enable large-scale deployment. The survey highlights open challenges and emerging opportunities in FL, offering insights into future research directions for building efficient and robust federated systems.
The integration of Social Media (SM) and the Internet of Things (IoT) is gradually transforming the activities of SM users into valuable data streams that can be analyzed using Machine Learning (ML) algorithms. Federated Learning (FL) has been widely employed to predict user and anomaly behaviors from distributed systems. However, FL encounters substantial security challenges, particularly within the context of SM-integrated IoT systems, known as SM 3.0 systems. These challenges encompass issues of accountability and vulnerabilities that render them susceptible to various cyberattacks, including single-point-of-failure, free-riding, model inversion, and poisoning attacks. We propose a Blockchain-enabled FL with Smart Contracts (SC) (BFL-SC) framework. To coordinate the learning process, track participantsâ contributions and reward the participants transparently, an SC-based FL is constructed as an incentive mechanism that combats free-riding attacks and enables automated and auditable rewarding of the participants. Also, to conceal the original data points and mitigate the impact of model inversion attacks, a Differentially Privacy-based Perturbation (DPP) mechanism is proposed. To address potential poisoning attacks, a thorough verification protocol is suggested. The experimental results obtained from two datasets, namely SM 3.0 and Human Activity Recognition (HAR), show that the BFL-SC framework can achieve high utility with a precision of 96.95% over the SM 3.0 dataset and 90.14% over the HAR dataset while adhering to privacy and efficiency standards, compared with compelling techniques.
The convergence of artificial intelligence and blockchain technology offers a compelling paradigm for deploying secure, auditable, and decentralisedintelligent systems in distributed environments where trust between participants cannot be assumed. Existing AI deployment frameworks lackimmutable audit trails, transparent model governance, and cryptographic integrity guarantees â requirements increasingly mandated by regulatoryframeworks including the EU AI Act and GDPR. This study presents ChainMind, a blockchain-enabled secure intelligent system frameworkintegrating smart contract-governed model lifecycle management, federated learning with on-chain gradient verification, and zero-knowledge proof(ZKP)-based inference auditing for privacy-preserving accountability. ChainMind was deployed and evaluated across three distributed intelligentsystem applications: a decentralised medical AI consortium (6 European hospitals, 284,000 patient records), a cross-border financial fraud detectionnetwork (4 banks, Germany and Italy), and a smart city data marketplace (Stuttgart urban IoT network, 12,400 sensors). ChainMind achieved modeltampering detection accuracy of 99.97%, federated learning convergence within 18.3% fewer rounds than standard FedAvg under adversarialgradient poisoning, and ZKP inference verification latency of 47.3 ms â compatible with real-time deployment. These results establish ChainMind asa technically viable and regulatory-compliant framework for blockchain-enabled secure AI in distributed environments.
Folding schemes are an exciting new primitive, transforming the task of performing multiple zero-knowledge proofs of knowledge for a relation into performing just one zero-knowledge proof, for the same relation, and a number of cheap inclusion-proofs. Recently, folding schemes have been used to amortize the cost associated with proving different statements to multiple distinct verifiers, which has various applications. We observe that for these uses, leaking information about the statements folded together can be problematic, yet this happens with previous constructions. Towards resolving this issue, we give a natural definition of privacy preserving folding schemes, and what security they should offer. To construct privacy preserving folding schemes, we first define statement hiders, a primitive which might be of independent interest. In a nutshell, a statement hider hides an instance of a relation as a new instance in the same relation. The new instance is in the relation if and only if the initial instance is. With this building block, we can utilize existing folding schemes to construct a privacy preserving folding scheme, by first hiding each of the statements. Folding schemes allow verifying that a statement was folded into another statement, while statement hiders allow verifying that a statement was hidden as another statement.
This paper presents a comprehensive review of the technological advancements, practical applications, inherent challenges, and emerging trends shaping the field of mobile biometrics. Over the past decade, the domain has evolved from basic fingerprint sensors to sophisticated multimodal systems leveraging AI-driven physiological and behavioral biometrics. The analysis examines the vast opportunities in finance, health-care, and digital identity management, while emphasizing the critical need to address privacy, security, regulatory, and ethical concerns. Furthermore, the study underscores the importance of collaborative efforts, highlighting promising future directions such as decentralized biometric storage and blockchain integration to enable secure and user-centric mobile experiences.
Federated Learning (FL) has emerged as a transformative approach to distributed machine learning, enabling the collaborative training of models across decentralized and private datasets. Unlike traditional centralized learning paradigms, FL ensures data privacy by keeping raw data localized on client devices while leveraging aggregated updates to build global models. This survey explores the critical aspects of efficient federated learning, including communication reduction, robustness to system and data heterogeneity, and scalability in real-world applications. We discuss key techniques such as model compression, asynchronous updates, personalized learning, and robust aggregation to address challenges posed by resource-constrained devices, non-IID data distributions, and adversarial environments. Applications of FL across diverse domains, including healthcare, finance, smart cities, and autonomous systems, highlight its potential to transform industries while preserving privacy and compliance with regulatory frameworks. The survey also identifies open challenges in scalability, privacy guarantees, fairness, and ethical considerations, providing future research directions to address these gaps. As FL continues to evolve, it holds the promise of enabling privacy-preserving, collaborative intelligence on a global scale, fostering innovation while addressing critical societal and technical challenges.
Ahmed Ayoub Bellachia, Mouhamed Amine Bouchiha, Yacine Ghamri-Doudane, Mourad Rabah
Blockchain-based Federated Learning (BFL) is an emerging decentralized machine learning paradigm that enables model training without relying on a central server. Although some BFL frameworks are considered privacy-preserving, they are still vulnerable to various attacks, including inference and model poisoning. Additionally, most of these solutions employ strong trust assumptions among all participating entities or introduce incentive mechanisms to encourage collaboration, making them susceptible to multiple security flaws. This work presents VerifBFL, a trustless, privacy-preserving, and verifiable federated learning framework that integrates blockchain technology and cryptographic protocols. By employing zero-knowledge Succinct Non-Interactive Argument of Knowledge (zk-SNARKs) and in-crementally verifiable computation (IVC), VerifBFL ensures the verifiability of both local training and aggregation processes. The proofs of training accuracy and aggregation are verified on-chain, guaranteeing the integrity and auditability of each participant's contributions. To protect training data from inference attacks, VerifBFL leverages differential privacy. Finally, to demonstrate the efficiency of the proposed protocols, we built a proof of concept using emerging tools. The results show that generating proofs for local training and aggregation in VerifBFL takes less than 81s and 2s, respectively, while verifying them on-chain takes less than 0.6s.
Advanced connection and autonomous features are being made possible by the Internet of Vehicles (IoV), which is causing a revolution in transportation. Strong security measures are required, however, because the prevalence of connected devices also increases the likelihood of cyberattacks and data breaches. This study introduces a new method for protecting IoV networks, which combines Blockchain technology with Quantum Key Distribution (QKD), creating a security architecture with two layers. Internet of Vehicles (IoV) technologies enable autonomous driving and real-time data exchange by connecting vehicles to infrastructure and one another. These advancements make things safer and more efficient, but they also put sensitive information at risk of cyberattacks. Modern security measures are essential since traditional encryption methods are becoming more and more insecure. To provide encryption that is theoretically unbreakable, the suggested system uses QKD to create and distribute cryptographic keys based on principles of quantum mechanics. To improve trust and transparency, blockchain technology is used to record these keys and any subsequent transactions in an immutable, distributed ledger. A hybrid architecture, with QKD securing the key exchange and Blockchain ensuring the integrity and authenticity of the communication, is designed as part of the integration process. Improved security and speed have been shown in simulations and prototype implementations of the QKD-Blockchain architecture in IoV networks. By preventing eavesdropping and key interception, the QKD technique kept the communication channel secure. With an average delay of only about 2 milliseconds, QKD performed admirably and was well below the permitted range for real-time vehicular communications. On average, validation durations for transactions were 5 milliseconds, which was a little overhead due to blockchain integration. The system efficiently handled up to 10,000 transactions per second without affecting security or performance, proving that it can serve massive IoV networks, according to scalability testing. Under high-load scenarios, the framework maintained consistent performance and security, proving its robustness in stress tests. Together, QKD and Blockchain provide a scalable and trustworthy option for future vehicular communication networks, and these results show how feasible and robust it is to use them to protect IoV systems. An intriguing approach to the security issues plaguing IoV systems is the integration of QKD with Blockchain technology. An unparalleled level of protection against cyber threats is provided by the dual-layered system, which guarantees strong encryption and data integrity. This fresh method may lead to improved and more trustworthy IoV networks by establishing new benchmarks for secure vehicular communication. In order to optimize the implementation and tackle any new issues that may arise, more research and development should be conducted.