Seid Mehammed, Girma Bewuketu, Demeke Getaneh, Md Nasre Alam · 6 authors
We present a permissioned blockchain–audited federated learning (FL) framework that strengthens data provenance and model‐update integrity. Our contribution is primarily engineering and architectural: a modular two‐channel design (provenance vs. update‐audit), lightweight on‐chain validation with off‐chain analytics, and a practical mapping to the 1 + 5 architectural views. In a TensorFlow Federated + Hyperledger Fabric prototype with 10 clients, we observe ≈18% faster anomaly detection under attack and a + 0.4 pp accuracy delta versus a baseline FL setup, with ~6% communication and ~8% energy overhead. We also provide a proof‐of‐concept zero‐knowledge succinct noninteractive argument of knowledge (zk‐SNARK) flow to validate per‐client summary properties off‐chain while anchoring results on‐chain. These contributions collectively advance the practical deployment of secure, auditable FL systems.
Modern enterprises generate vast volumes of data across distributed applications, cloud platforms, and digital services. Traditional centralized data governance models struggle to scale in such complex environments, leading to data silos, inconsistent governance enforcement, and limited data accessibility. Autonomous data platforms supported by artificial intelligence (AI) offer a promising solution by integrating self-service infrastructure, automated governance mechanisms, and intelligent metadata management. AI-driven governance frameworks can automate tasks such as data discovery, classification, lineage tracking, anomaly detection, and compliance monitoring. This article explores the architectural foundations of autonomous data platforms and examines how AI-driven governance enables scalable, decentralized, and trustworthy data ecosystems. Drawing on emerging concepts such as data mesh architectures, federated governance models, and responsible AI frameworks, the paper proposes a conceptual model for building intelligent and self-governing enterprise data platforms. In such environments, machine learning algorithms continuously analyze data flows, schema evolution, usage patterns, and policy compliance to dynamically enforce governance rules and improve data quality. Metadata-driven architectures further enable automated cataloging, semantic enrichment, and real-time lineage tracking, allowing organizations to maintain transparency and accountability across complex data pipelines. By embedding governance directly into the data infrastructure, autonomous platforms reduce operational overhead while empowering domain teams to manage their own data products within standardized governance policies. Furthermore, the integration of explainable AI techniques and policy-aware automation ensures that governance decisions remain auditable, fair, and aligned with regulatory requirements. Ultimately, the convergence of AI, distributed data architectures, and intelligent metadata management provides a scalable foundation for building resilient, adaptive, and trustworthy enterprise data ecosystems capable of supporting advanced analytics, machine learning, and data-driven decision-making.
Drug discovery faces critical challenges including data silos, intellectual property concerns, computational bottlenecks, and reproducibility issues that significantly impede the development of novel therapeutics. This research proposes a novel Blockchain-enabled Federated Learning Framework for Drug Discovery (BFLD) that integrates distributed ledger technology, federated machine learning, and molecular docking simulations to create a secure, transparent, and collaborative ecosystem for pharmaceutical research. Our framework addresses key limitations in traditional drug discovery pipelines by enabling multi-institutional collaboration without compromising proprietary data, ensuring immutable audit trails for compound screening results, and accelerating hit-to-lead optimization through decentralized computing. We evaluate BFLD using datasets from 12 pharmaceutical research institutions, encompassing 2.4 million molecular compounds and 847 protein targets. Results demonstrate a 68% reduction in lead compound identification time, 91% improvement in data provenance tracking, and 94% stakeholder confidence in intellectual property protection. The framework achieves 89.7% accuracy in toxicity prediction through federated learning models while maintaining complete data privacy. Smart contracts automate licensing agreements and ensure equitable attribution of discoveries across participating institutions. This research establishes a paradigm shift toward decentralized, trustless pharmaceutical innovation aligned with open science principles while protecting commercial interests.
Enterprise Information Systems have a long-established and crucial role for modern organizations, as they enable seamless integration and management of critical business processes, ensuring efficiency in operations, data accuracy, and enhanced decision-making capabilities. One of their most interesting emerging technologies refer to the use of Artificial Intelligence as they may seamlessly automate routine tasks, offer predictive analytics, and provide deep insights, ultimately leading to intelligent data-driven decisions and improved operational efficiency. Of course, this direction of work is accompanied by some important challenges that come from the opacity of certain AI models and their potential biases due to low-quality training data used. In this paper, we argue that such challenges can be mitigated by a novel framework able to integrate, in a transparent manner, quality-related metadata on datasets used for training the AI-enabled emerging technologies in the field of EIS systems. These metadata are minted as Non-Fungible Tokens (NFTs) over the blockchain.
Ensuring the reproducibility of scientific simulations is a persistent challenge, despite current best practices like version control and containerization. Factors such as floating-point arithmetic variations, hardware differences, and concurrency issues often prevent bit-for-bit replication of results. This paper investigates the techniques that distributed ledger technologies employ to achieve deterministic computations and application of these techniques to enhance the reproducibility, trustworthiness and verifiability of scientific simulations. We explore two primary approaches: executing simulations directly “on-chain” for complete transparency and deterministic replay, and performing computations “off-chain” while anchoring their integrity to a blockchain via cryptographic proofs, such as Zero-Knowledge Proofs (ZKPs) and Merkle trees.
Introduction Decentralized autonomous organizations in decentralized science face unique organizational and scientific demands. This study examines core challenges encountered by DeSci DAOs and how these challenges affect governance and research practice. Methods Ten semi-structured interviews were conducted with co‐founders, working‐group leads, and long‐term contributors. Transcripts were analyzed using Kuckartz’s six‐phase qualitative content analysis. Categories were developed and refined to synthesize recurrent themes across interviews. Results Nineteen sub-categories clustered into six domains: governance, financials, contribution, onboarding, operations, and science. Findings highlight tensions between token‐weighted decision making and domain expertise, labor‐intensive hybrid accounting practices, persistent talent shortages, steep Web3 onboarding curves, fragmented project coordination, and science‐specific issues that include negotiations with technology transfer offices and the tokenization of research assets. The resulting category system provides a diagnostic baseline for understanding how decentralized governance intersects with scientific rigor. Discussion DeSci DAOs progress most effectively when blockchain-enabled transparency is paired with clearly defined coordination roles, structured onboarding pathways, and credible mechanisms for scientific validation. These features help balance organizational experimentation with proven practices and support more reliable scientific workflows.
Igor Calzada, Géza Németh, Mohammed Salah Al-Radhi
As generative AI (GenAI) technologies proliferate, ensuring trust and transparency in digital ecosystems becomes increasingly critical, particularly within democratic frameworks. This article examines decentralized Web3 mechanisms—blockchain, decentralized autonomous organizations (DAOs), and data cooperatives—as foundational tools for enhancing trust in GenAI. These mechanisms are analyzed within the framework of the EU’s AI Act and the Draghi Report, focusing on their potential to support content authenticity, community-driven verification, and data sovereignty. Based on a systematic policy analysis, this article proposes a multi-layered framework to mitigate the risks of AI-generated misinformation. Specifically, as a result of this analysis, it identifies and evaluates seven detection techniques of trust stemming from the action research conducted in the Horizon Europe lighthouse project called Enfield: (i) federated learning for decentralized AI detection, (ii) blockchain-based provenance tracking, (iii) Zero-Knowledge Proofs for content authentication, (iv) DAOs for crowdsourced verification, (v) AI-powered digital watermarking, (vi) explainable AI (XAI) for content detection, and (vii) Privacy-Preserving Machine Learning (PPML). By leveraging these approaches, the framework strengthens AI governance through peer-to-peer (P2P) structures while addressing the socio-political challenges of AI-driven misinformation. Ultimately, this research contributes to the development of resilient democratic systems in an era of increasing technopolitical polarization.
This research proposes a Blockchain-driven solution for enhancing the integrity and security of clinical trials, introducing a specialized system called Blockchain for Securing Clinical Trials (BC-SCT). The system reimagines traditional clinical trial data management by offering a decentralized, tamper-resistant platform that ensures trust, transparency, and efficiency across stakeholders including researchers, sponsors, and regulatory bodies.BC-SCT employs modern consensus mechanisms such as Proof-of-Authority (PoA) and Delegated Proof of Stake (DPoS) to significantly reduce transaction processing delays—from 900 ms to 550 ms across 50 transactions—ensuring faster data validation without compromising reliability. It also demonstrates strong performance under simultaneous query loads, cutting response times from 70 ms to 40 ms, a 43% improvement in real-time data access. To handle the scale and complexity of clinical data, the system incorporates features like data sharding, in-memory caching, and off-chain storage. These enhancements reduce Blockchain ledger load by 20%, lowering storage requirements from 100 GB to 80 GB for 10,000 entries—while maintaining high-speed access and data fidelity. Through these innovations, BC-SCT offers a future-proof foundation for conducting and overseeing clinical trials, addressing long-standing issues related to data manipulation, inefficiency, and lack of transparency in research workflows.
In recent years, the utilization of Ethereum has significantly increased, positioning it as a favored platform among criminal entities. A recently proposed blacklisting method offers a compelling approach; however, its implementation faces numerous challenges. For instance, criminals may circumvent the blacklisting mechanism by creating new addresses and there are several ambiguities in their explanation. This paper explores the increasing use of Ethereum for criminal activities, focusing on the challenges of enforcing blacklisting to curb illegal transactions. We analyse blacklisting within cryptocurrency networks, particularly Ethereum, and develop features to detect illegal patterns. The study identifies unique issues in transaction networks that require specialised solutions beyond general cryptocurrency techniques. We propose a detection model based on these features and validate its effectiveness using real Ethereum datasets. The paper also reviews regulatory guidelines, highlighting ambiguities in their interpretation. Experiments on real-world data underscore the need to integrate technical methods and consider Shapley-value-based frameworks in designing effective solutions. The novelty of the method lies in its development of a feature-based detection model, leveraging Shapley-value frameworks to enhance explanation, address Ethereum’s unique challenges, and empirically validate its effectiveness using real Ethereum data, offering a more robust solution than traditional blacklisting approaches.
In response to the growing demand for enhanced performance and power efficiency, the semiconductor industry has witnessed a paradigm shift toward heterogeneous integration, giving rise to 2.5D/3D chips. These chips incorporate diverse chiplets, manufactured globally and integrated into a single chip. Securing these complex 2.5D/3D integrated circuits (ICs) presents a formidable challenge due to inherent trust issues within the semiconductor supply chain. Chiplets produced in untrusted locations may be susceptible to tampering, introducing malicious circuits that could compromise sensitive information. This paper introduces an innovative approach that leverages blockchain technology to establish traceability for ICs and chiplets throughout the supply chain. Given that chiplet manufacturers are dispersed globally and may operate within different blockchain consortiums, ensuring the integrity of data within each blockchain ledger becomes imperative. To address this, we propose a novel dual-layer approach for establishing distributed trust across diverse blockchain ledgers. The lower layer comprises of a blockchain-based framework for IC supply chain provenance that enables transactions between blockchain instances run by different consortiums, making it possible to trace the complete provenance DAG of each IC. The upper layer implements a multi-chain reputation scheme that assigns reputation scores to entities while specifically accounting for high-risk transactions that cross blockchain trust zones. This approach enhances the credibility of the blockchain data, mitigating potential risks associated with the use of multiple consortiums and ensuring a robust foundation for securing 2.5D/3D ICs in the evolving landscape of heterogeneous integration.
The rapid evolution of Ethereum’s infrastructure calls for innovative mechanisms to enhance scalability, security, and performance. This paper introduces BeamSNARKS, a cutting-edge framework designed to address critical challenges in zero-knowledge proof systems. BeamSNARKS encompasses two groundbreaking innovations: the Dynamic zkSNARKS Generation Optimization Mechanism and the Dynamic SNARKification Technology. The former revolutionizes computational efficiency by dynamically retrieving state data relevant to proof generation, minimizing bandwidth and storage requirements while maintaining validation accuracy. The latter introduces adaptive circuit design and hierarchical proof aggregation to optimize transaction throughput and reduce the computational and financial overhead of Layer 1 submissions. Together, these innovations establish BeamSNARKS as a pivotal advancement in scalable, efficient, and resource-optimized zero-knowledge proof systems. Through comprehensive analysis and targeted experiments, this paper evaluates the performance of BeamSNARKS’s innovations, demonstrating their potential to transform Ethereum’s decentralized ecosystem and lay the groundwork for future high-throughput applications.
Blockchain technology, known for its immutable distributed ledger, which greatly improves the credibility of data management in various applications. However, the immutability may result in erroneous data being permanently stored in the blockchain, affecting the security of the blockchain system. To address this issue, redactable blockchain is proposed to allow flexibly modifications of erroneous data in blockchain. Despite their promise, current redactable blockchain solutions often fall short in balancing two critical aspects: decentralization and data accountability. In this paper, we propose a Decentralized, Accountable and Redactable Blockchain solution (DARB). Our solution aims to mitigate the risks associated with central authority while ensuring secure accountability in data modification processes. Decentralization is achieved by using authorized authorities instead of the central authority, utilizing decentralized ciphertext policy attribute-based encryption. Additionally, it incorporates traceable ring signatures, which enable the authorized authorities to collaborate effectively in holding edited data accountable and tracing the identity of malicious modifiers. The security analysis and experimental results demonstrate that the DARB scheme successfully facilitates secure data rewriting and ensures accountability, all while maintaining an acceptable level of additional time overhead.
This work presents the DGChain (Data-Git- for Blockchain) project. This Python package allows version control of data in blockchain and IPFS based on a DAO (decentralized autonomous organization) for managing data in the development cycles of reproducible computational scientific research. Analyzes the benefits of using this Blockchain-Based Decentralized Architecture to mediate collaborative interactions between developers compared to existing solutions. Presents a use case in developing a medical research project and typical IRIS example to offer the traceability of changes and provenance of metadata, data, and code in Data / Software Version Control systems through management of intrinsic hash-based persistent, immutable CIDs (Content Identifier) recorded in Merkle trees in the development cycle of its main products, publication, software source code, and Data to guarantee reproducibility and trustworthiness in computational scientific research using DGChain.
Junyi Zhong, Thiago Abreu, Sami Souihi, Françoise S. Lucas
This paper introduces the G-TOK framework, which utilizes advanced zero-knowledge proofs (ZKPs) and dynamic verifiable credentials (VCs) to preserve data privacy in sensor data sharing on blockchain networks. As industries increasingly depend on accurate and confidential sensor data from IoT applications, maintaining privacy and data integrity becomes a significant challenge. Our framework specifically addresses this issue in the context of smart environment sensor networks. Typically, data access control in such networks is either fully permissioned or overly restrictive, lacking mechanisms for selective disclosure access control. Our approach aims to enhance encrypted decentralized data storage and improve data interoperability. It includes dynamic VCs, authenticated privacy-preserving tokenization of geolocation data, and a decentralized real-time location verification scheme. Additionally, we propose a proof-of-footprint (PoF) schema, showcasing the integration and practicality of cutting-edge technologies such as ZKPs, VCs, and self-sovereign identities. This schema aligns with international standards, including the Verifiable Credentials Data Model v2.01and selective disclosure of JSON Web Token (JWT) claims2.
In database applications involving sensitive data, the dual imperatives of data confidentiality and provable (verifiable) query processing are important. This paper introduces PoneglyphDB, a database system that leverages non-interactive zero-knowledge proofs (ZKP) to support both confidentiality and provability. Unlike traditional databases, PoneglyphDB enhances confidentiality by ensuring that raw data remains exclusively with the host, while also enabling verifying the correctness of query responses by providing proofs to clients. The main innovation in this paper is proposing efficient ZKP designs (called circuits) for basic operations in SQL query processing. These basic operation circuits are then combined to form ZKP circuits for larger, more complex queries. PoneglyphDB's circuits are carefully designed to be efficient by utilizing advances in cryptography such as PLONKish-based circuits, recursive proof composition techniques, and designing with low-order polynomial constraints. We demonstrate the performance of PoneglyphDB with the standard TPC-H benchmark. Our experimental results show that PoneglyphDB can efficiently achieve both confidentiality and provability, outperforming existing state-of-the-art ZKP methods.
With the rapid development and increasing maturity of emerging technologies such as 5G communication, artificial intelligence, blockchain technology, and computer supported collaborative work, the internet is entering a new era - Web3. This transformation brings both opportunities and challenges to the field of education. Addressing current issues faced by universities, such as security risks in resource storage, lack of platform creation incentives, complexity in copyright confirmation, unsatisfactory user interaction experiences, and insufficient supply of high-quality educational resources, this paper explores and proposes an innovative solution - the “CoTeach” smart education platform. This platform integrates the core concepts of Web3, and data-driven artificial intelligence technology. It aims to reshape the teaching and learning experience, as well as the collaborative development of professional knowledge. Specifically, the “CoTeach” platform ensures secure storage and immutability of educational resources through blockchain technology, reducing risks associated with resource storage. By utilizing collaborative livestreaming mechanisms, it provides economic incentives for creators, contributors, and learners, fostering greater community participation. The transparency and smart contract functionality of blockchain simplify the copyright confirmation process, safeguarding creators' rights. The platform enhances user interaction through gamification design, making the learning process more engaging and enjoyable. Finally, artificial intelligence technology optimizes resource recommendations and personalized learning paths, addressing the shortage of high-quality educational resources.
Jan Lauinger, Jens Ernstberger, Andreas Finkenzeller, Sebastian Steinhorst
Web users can gather data from secure endpoints and demonstrate the provenance of sensitive data to any third party by using privacy-preserving TLS oracles. In practice, privacy-preserving TLS oracles remain limited and cannot verify larger, sensitive data sets. In this work, we introduce new optimizations for TLS oracles, which enhance the efficiency of selectively verifying the provenance of confidential web data. The novelty of our work is a construction which secures an honest verifier zero-knowledge proof system in the asymmetric privacy setting while retaining security against malicious adversaries. Concerning TLS 1.3 in the one round-trip time (1-RTT) mode, we propose a new, optimized garble-then-prove paradigm in a security setting with malicious adversaries. Our improvements reach new performance benchmarks and facilitate a practical deployment of privacy-preserving TLS oracles in web browsers.
Domingo Ranieri, Alessandro COSTANTINI, Barbara Martelli
In recent years, blockchain has emerged as a promising new technology to manage trusted information, making it easier for companies to access and use critical data while maintaining the security of this information. Permissioned blockchains, unlike permissionless ones, restrict access to a select group of certified entities. They ensure a controlled and secure environment where only authorized participants can join the network and perform operations, a peculiar aspect in sectors where data sensitivity, confidentiality, and limited access are crucial. Tracking operations performed on the data and guaranteeing reproducibility of research through workflow reconstruction upon data processing become very important in different sectors ranging from scientific communities to private companies and health. This is the case of the present activity, where the implementation of a permissioned blockchain system aimed at ensuring data immutability, operations traceability, and the ability to reproduce workflows is presented and discussed. In such regards, we work with Hyperledger Fabric, an enterprise-grade permissioned distributed ledger platform that offers modularity and versatility for a broad set of industry use cases.
Tarek Zaarour, Ahmed Khalid, Preeja Pradeep, Ahmed H. Zahran
Knowledge graphs have proven vital for efficient data management, enhanced search capabilities, and improved decision-making in various information technology domains. However, constructing reliable knowledge graphs in decentralized ecosystems, with distributed autonomous actors, poses significant challenges related to asynchronous transmission, out-of-order knowledge-sharing, device heterogeneity, and trust issues. These challenges are also present in resource orchestration within multi-cloud edge ecosystems where multiple stakeholders must collaborate and share information to enable next-gen smart applications. In this paper, we propose a novel system design that utilizes Distributed Ledger Technology to build knowledge graphs. This approach ensures consistent and trustworthy knowledge sharing among orchestrators in a cloud-edge continuum. Our solution accommodates diverse requirements of both cloud and edge servers, allowing clients to construct complete historic graphs or build filtered sub-graphs. We deploy our solution in a multi-cloud edge environment and construct knowledge graphs representing the system state, including clusters, servers, microservices, and various resources. We validate the feasibility and performance of our solution through a real-world deployment and experiments in a smart shopping use case. Results demonstrate that the proposed solution achieves the claimed benefits with minimal or acceptable delays in comparison to traditional event streaming services.