Chandni Patel, Parth Sheth, Megh H. Shah, Dev Mehta · 8 authors
One of the main issues with the Industrial Internet of Things (IIoT) in V2X communication is the threat of attacks. A comprehensive Intrusion Detection System (IDS) and a transparent ledger are important for providing an Intelligent Transportation System (ITS) beyond 5G. However, another major problem is that it is centralized and lacks a clear explanation of traditional IDS. By integrating Federated Learning (FL) to make it distributed and Explainable AI (XAI) to add a brain to the black box model to add the explanation factor, we make the model more robust and suitable for real-life situations. In this approach, we experimented using the X-IIOTID dataset. This dataset is a real-time indicator of the attack in an IIoT network such as V2X. It provides difficult and real-time scenarios that highlight the complexity of IDS. Furthermore, the benign data the model classifies is stored in the blockchain to make the system secure and transparent. Our FL-XAI-based technique provides an accuracy of $98 \%$ results than previous models. The proposed approach provides a clear and brief view of factors that affect classification actions, which helps users make security decisions. Evaluation of Pravah based on latency, accuracy, precision, recall, F1-score, and ROC-AUC confirms its effectiveness. This study contributes towards a more secure and interpretable ITS, bridging the gap between model performance and real-world applicability.
In today's rapidly advancing healthcare landscape, integrating Artificial Intelligence (AI) and Machine Learning (ML) has the potential to significantly improve patient care and streamline medical processes. The utilization of confidential patient data to train and develop these technologies, however, raises significant concerns regarding authenticity, security, and privacy. In this study, we introduce MediChainAI, a safe and practical framework that allows patients full ownership over their own health data by integrating Self-Sovereign Identity (SSI), Blockchain, and sophisticated cryptography techniques. By clearly outlining the goals and parameters of this access, MediChainAI allows patients to safely and selectively share data with healthcare providers and researchers. While SSI guarantees that patients have ownership of their data, the framework uses Blockchain technology to keep things transparent and secure. Further, MediChainAI makes use of Merkle trees, which provide verified access to subsets of data without jeopardizing the privacy of the whole dataset. The encryption mechanism, which is based on smart contracts, is a distinctive feature of the framework that allows researchers and medical practitioners controlled and secure access to patient data. In order to improve the accuracy and reliability of medical diagnoses and treatment, this strategy makes sure that only confirmed, legitimate data is utilized to train medical models. A significant step toward safer and more personalized healthcare, MediChainAI encourages ethical and patient-focused innovation by effectively resolving essential issues regarding data security and patient privacy.
Open access
2 source records
Blockchain Technology Applications and Security
Privacy-Preserving Technologies in Data
Artificial Intelligence in Healthcare and Education
Alejandro Peñuelas-Angulo, Claudia Feregrino-Uribe, Morales-Sandoval Miguel
Multi-authority Attribute-based Encryption (MAABE) schemes distribute the responsibility of managing the scheme attributes and attribute keys among several attribute authorities. However, MA-ABE schemes often assume that the attribute authorities are always fully trusted parties and lack authenticity checks. This paper proposes a Ciphertext-Policy MAABE scheme that incorporates a user-authority mutual authentication mechanism exploiting the properties of Zero-Knowledge Proofs. A batch version of the Schnorr protocol validates the authority identity and the possession of claimed attribute keys. The complete scheme is enhanced using asymmetric pairings to improve security and performance. Furthermore, outsourced decryption is considered to exploit the available computing resources under a fog-enabled IoT environment. The proposed scheme's analysis shows the overall construction's efficiency and, particularly, the efficiency and suitability of the mutual verification protocol.
Thanassis Tiropanis, George Roussos, Mohammad Bahrani, Mohamed Ragab
The growing demand for data ownership and privacy is reshaping how information is accessed, managed, integrated, and recommended. Building on the inaugural DESERE workshop at The Web Conference 2024, this second edition advances research on Decentralised Search and Recommendation platforms such as Personal Online Datastores (PODs), where users retain control of their data and explicitly manage permissions. As ecosystems decentralise, traditional information retrieval must be revisited while standards for new techniques and system designs are developed to ensure efficient, accurate, and privacy-preserving search. The Second DESERE workshop at CIKM 2025 focuses on infrastructures and retrieval algorithms for user-controlled data. It convenes a cross-disciplinary community spanning data retrieval, management and integration, semantic technologies, recommendation systems, privacy-aware computing, and search efficiency to explore approaches that prioritize user agency, data ownership, and scalable retrieval across PODs and related architectures. Through paper presentations, panels, and interactive sessions, the workshop will highlight challenges, opportunities, and solutions for privacy-preserving IR. These discussions are especially relevant to domains where user-centric design and data stewardship are critical-such as personal finance, education, and high-stakes areas like criminal justice and health.
Rui Shi, Huamin Feng, Chunjie Cao, Yang Yang · 6 authors
Anonymous credentials are an essential cryptography primitive to protect user privacy and provide fine-grained access control for proving ownership and rights of specific credentials. There are currently two roadmaps to designing anonymous credentials: one is signature credentials, which are constructed by signature with efficient protocols and non-interactive zero-knowledge proofs, and the other is functional credentials, which are transformed from predicate encryption schemes. However, none of the existing instances of anonymous credentials support$expressive$access policies expressed as conjunction, disjunction, or arbitrary Boolean formulas, which are particularly useful for cloud services. In this paper, we propose a new fast and expressive anonymous credential, called FEAC. It is constructed with the unique$dual$$randomness$$splitting$technique, which combines the most efficient anonymous key-policy attribute-based encryption (USENIX 24) and short randomizable signature (CT-RSA 18) to balance efficiency, expressiveness, and security, demonstrating a new way to instantiate anonymous credentials. Furthermore, our credential presentation protocol offloads most of the time-consuming computation to the cloud server (11 pairing) to reduce the computational burden on the user side (2 pairing). We propose formal definitions and formal security proofs of FEAC. We provide implementations and evaluate the performance of FEAC, comparing it to state-of-the-art work.
Wencheng Chen, Jun Wang, Jeng‐Shyang Pan, R. Simon Sherratt · 5 authors
With the rapid expansion of sensor networks across domains such as environmental monitoring, industrial automation, and smart healthcare, ensuring secure and reliable data storage in resource-constrained environments has become a critical challenge. Traditional centralized storage systems struggle with data tampering, privacy leakage, and vulnerability to collusion among nodes. Blockchain technology, characterized by decentralization, immutability, and traceability, provides a promising foundation for trustworthy sensor data management. Among various consensus mechanisms, Delegated Proof of Stake (DPoS) has been recognized for its efficiency and low energy consumption, yet it faces two critical issues: limited incentives for ordinary sensor nodes to participate in voting and the risk of collusion that undermines fairness and stability. To overcome these limitations, this study proposes a blockchain-enabled sensor data storage framework incorporating a four-party evolutionary game model. The model explicitly captures the strategic interactions among cluster head nodes, ordinary sensor nodes, competing gateway nodes, and supervisory nodes, while integrating reputation evaluation, penalty enforcement, and supervisory oversight. Through evolutionary game analysis, the proposed framework reveals the stability conditions of node behaviors and identifies strategies that promote fair and secure consensus. Simulation results verify that the mechanism enhances node participation, suppresses collusion, accelerates consensus convergence, and achieves superior throughput and fault tolerance compared with existing schemes. This research provides theoretical insights and practical guidance for designing secure, efficient, and scalable blockchain-enabled sensor network data storage systems.
Blockchain and Federated Learning (FL) provide a strong framework for distributed, privacypreserving machine learning in the medical field. In order to provide safe and effective model training, this framework assists in handling sensitive patient data from lung disease diagnosis, such as CT scans, X-rays, and clinical records. The proposed approach improves distributed machine learning security, privacy, and integrity, particularly in delicate fields like healthcare. Contributions from other datasets help the model get better, but patient data is kept private and blockchain guarantees the integrity of the updates to the model. ZeroKnowledge Proofs (ZKP) guarantee that customers can demonstrate the accuracy of their model upgrades without disclosing any personal information. FLBC- ZKP uses cryptographic proofs to remove this requirement for confidence. FLBC-ZKP models exhibit competitive accuracy rates in healthcare applications, guaranteeing confidentiality and privacy without compromising predictive performance. Contri- butions from other datasets improve the model, but patient information is kept confidential and the blockchain ensures the accuracy of model updates. Compared to regular FL, FLBC-ZKP delivers superior privacy and security through blockchain and ZKP, making it particularly suitable for sensitive healthcare data, while maintaining high accuracy. The accuracy data throughout federated learning rounds for a different approach, FLBC-ZKP slightly surpasses the other methods as the number of rounds increases.
K. Ramesh Babu, M. Ramesh, M Gnana Prasuna, G. Ganesh Kumar · 6 authors
This article presents the Adaptive Multi-Modal Federated Optimization (AMMFO) framework which was developed to tackle important challenges in data privacy, fairness, and accountability in learning in the context of federated learning. The AMMFO framework addresses the need to train models with data from multiple modalities available at the edge in a secure and efficient manner while building trust and respecting privacy in a decentralized system. AMMFO applies differential privacy to protect sensitive model updates from adversarial inference and it leverages a blockchain-based trust mechanism to allow for transparency, immutability and decentralized accountability. The framework optimally adapts learning across multiple data modalities enhancing communication efficiency and stability of model convergence. Results from experiments indicate that AMMFO achieves 8-10% higher accuracy compared to FedAvg and FedProx, and 7-12% greater privacy resistance compared to FedDP while exploring different privacy budgets. Additionally, AMMFO improves convergence time by 15–20 percent and achieves less than 8% blockchain overhead. Overall, these results demonstrate the AMMFO framework's balance of performance, privacy, and scalability which enables next generation AI systems that are situated within privacy and trust-worthy frameworks in domains such as healthcare, finance, autonomous systems, and smart cities.
Rana Alaa, Darío González-Ferreiro, Carlos Beis-Penedo, Manuel Fernández‐Veiga · 6 authors
Split learning is an approach to collaborative learning in which a deep neural network is divided into two parts: client-side and server-side at a cut layer. The client side executes its model using its raw input data and sends the intermediate activation to the server side. This configuration architecture is very useful for enabling collaborative training when data or resources are separated between devices. However, split learning lacks the ability to verify the correctness and honesty of the computations that are performed and exchanged between the parties. To this purpose, this paper proposes a verifiable split learning framework that integrates a zk-SNARK proof to ensure correctness and verifiability. The zk-SNARK proof and verification are generated for both sides in forward propagation and backward propagation on the server side, guaranteeing verifiability on both sides. The verifiable split learning architecture is compared to a blockchain-enabled system for the same deep learning network, one that records updates but without generating the zero-knowledge proof. From the comparison, it can be deduced that applying the zk-SNARK test achieves verifiability and correctness, while blockchains are lightweight but unverifiable.
Intrusion Detection Systems (IDS) play a critical role in protecting modern networks, but traditional centralized designs raise serious concerns regarding data privacy, trust, and scalability. Federated Learning (FL) reduces privacy risks through decentralized model training, and blockchain enhances trust by providing immutability and transparency. Combining these technologies creates a promising paradigm for secure and trustworthy IDS. This paper presents a comprehensive survey of blockchain-federated IDS with a particular focus on privacy and trust. The key contribution is a multi-dimensional taxonomy that integrates IDS architectures, FL strategies, blockchain types, and consensus mechanisms, providing a clear and structured view of this emerging field. We categorize threats into data, communication, and model levels, and map representative defense mechanisms to each. We also review applications in vehicular networks, industrial and medical Internet of Things (IoT), and metaverse scenarios. Finally, we highlight key challenges, including non-IID data, lightweight consensus, incentive mechanisms, and poisoning-resilient aggregation, and outline future research directions.
Mohammed Abdelhamid Nedioui, Ali Khechekhouche, Konstantinos Κarampidis, Giorgos Papadourakis · 5 authors
The integration of artificial intelligence (AI) and blockchain technology opens new avenues for decentralized, transparent, and secure data-driven systems. However, ensuring privacy and verifiability in collaborative AI environments remains a key challenge, especially when model updates or decisions must be recorded immutably on-chain. In this paper, we propose a novel privacy-preserving framework that leverages an ElGamal-based aggregate signature scheme with aggregate public keys to enable secure, verifiable, and unlinkable multi-party contributions in blockchain-based AI ecosystems. This approach allows multiple AI agents or data providers to jointly sign model updates or decisions, producing a single compact signature that can be publicly verified without revealing the identities or individual public keys of contributors. The design is particularly well-suited to resource-constrained or privacy-sensitive applications such as federated learning in healthcare or finance. We analyze the security of the scheme under standard assumptions and evaluate its efficiency in different terms. The study and experimental results demonstrate the potential of our framework to enhance trust and privacy in AI collaborations over decentralized networks.
The increasing value of data as a digital asset has motivated research on secure and privacy-preserving data trading frameworks. Traditional data exchange models expose raw datasets directly, leading to privacy leakage and unclear ownership attribution. This paper presents a blockchain-based data trading framework that integrates Non-Fungible Tokens (NFTs) for ownership verification and Generative Adversarial Networks (GANs) for privacy-preserving synthetic data generation. By leveraging differential privacy during GAN training, the framework ensures data usability while providing provable privacy guarantees. Experimental results on benchmark datasets demonstrate that the proposed model achieves a favorable trade-off between privacy and utility, supporting secure and efficient data circulation in decentralized environments.
Saurabh V. Magdum, Sonali Patil, Deepali Nilesh Naik
Federated Learning (FL) revolutionized the field preserving machine learning by facilitating collaborative model training among decentralized clients in absence of raw data. The classic architectures of FT, in contrast, usually rely on a centralized aggregator, which poses threats such as single points of failure, data poisoning, and model inversion attacks. Use of combination of Blockchain technology holds the promise solution via replacement of centralized aggregators with decentralized consensus mechanisms, improving trust, transparency, and data integrity. The present bibliometric analysis considers the correlation of Blockchain and Federated Learning (BFL), with special reference on flagship aggregation algorithms like FedAvg, FedProx, and FedBN, specifically the blockchain networks such as Ethereum, Hyper- ledger Fabric, and Polkadot. Additionally, the paper records actual- world use cases in privacy-sensitive applications like healthcare, finance, and IoT, using benchmark datasets such as MIMIC-III, NASDAQ stock data, and EdgeIIoTset. The proposed study identifies Key trends, timeless findings, and future directions In BFL, gaining perceptual insights of its growing significance for building trustworthy, privacypreserving AI systems.
Ping Wang, Fei Tang, Ankui Jing, Lei Liu · 6 authors
In vehicular ad-hoc networks (VANET), federated learning enables vehicles to collaboratively train global models for intelligent transportation without sharing raw data. However, global model training faces various potential risks, such as identity leakage, privacy inference, and malicious attacks, due to the dynamic network structure and untrusted wireless communication of VANET. To address these issues, a robust authentication mechanism for federated learning must be achieved to ensure the trustworthiness of model parameters. In this paper, we propose an efficient and privacy-preserving authentication scheme with lightweight encryption for federated learning in VANET using self-sovereign identity (SSI), called Fed-EALE. Fed-EALE constructs Merkle pseudonym identity trees with the aid of decentralized identifiers. Vehicle participants use unlinkable pseudonyms to achieve privacy protection. Fed-EALE utilizes verifiable credentials and zero-knowledge proof to build the authentication protocol to ensure the authenticity and integrity of model parameters from anonymous vehicles. In addition, to accurately identify and eliminate malicious participants in anonymous communications, Fed-EALE can track and recover the real identities of malicious vehicles. We perform a security analysis of Fed-EALE. Performance evaluations indicate that Fed-EALE reduces authentication overhead by approximately 76% compared to state-of-the-art protocols, while maintaining high stability and scalability in VANET.
Self-Sovereign Identity (SSI) frameworks enable individuals to receive and present digital credentials in a user-controlled way. Revocation mechanisms ensure that invalid or withdrawn credentials cannot be misused. These revocation mechanisms must be scalable (e.g., at national scale) and preserve core SSI principles such as privacy, user control, and interoperability. Achieving both is hard, and finding a suitable trade-off remains a key challenge in SSI research.This paper introduces UPPR, a revocation mechanism for One-Show Verifiable Credentials (oVCs) and unlinkable Anonymous Credentials (ACs). Revocations are managed using percredential Verifiable Random Function (VRF) tokens, which are published in a Bloom filter cascade on a blockchain. Holders prove non-revocation via a VRF proof for oVCs or a single Zero-Knowledge Proof for ACs. The construction prevents revocation status tracking, allows holders to stay offline, and hides issuer revocation behavior. We analyze the privacy properties of UPPR and provide a prototype implementation on Ethereum. Our implementation enables off-chain verification at no cost. On-chain checks cost 0.56–0.84 USD, while issuers pay only 0.00002–0.00005 USD per credential to refresh the revocation state.