This paper proposes a novel consensus mechanism for blockchain networks, termed Distributed Proof-of-Work with Differential Privacy Constraints (DPPoW). The core objective is to integrate differential privacy guarantees into a Proof-of-Work (PoW) system, mitigating the privacy vulnerabilities inherent in traditional blockchain designs. The proposed mechanism introduces calibrated noise directly into the hashing process, carefully controlled to achieve a specified ε-differential privacy level. Furthermore, it incorporates a distributed key generation scheme to bolster security and prevent centralized control. The design addresses the growing concern about data traceability and potential deanonymization of participants within blockchain networks. Mathematical formulations detail the noise injection process and the key generation protocol, demonstrating the feasibility and effectiveness of the approach. The primary innovation lies in the synergistic combination of PoW's security features with differential privacy, offering a robust solution for privacy-conscious blockchain applications. The system aims to balance security, anonymity, and computational efficiency, a challenging endeavor currently unmet by existing blockchain technologies.
Federated learning (FL) has emerged as a promising paradigm for training machine learning models on decentralized data, offering enhanced privacy and reduced communication costs. However, the inherent distributed nature of FL introduces significant challenges regarding trust, security, and model accuracy. This paper presents a formal verification framework for FL systems, leveraging secure multi-party computation (SMPC) and formal verification techniques to rigorously analyze data flow and model updates. The framework aims to provide guarantees about privacy, security, and model accuracy, addressing the unique vulnerabilities present in FL architectures. We define a mathematical model of an FL system, incorporating key elements such as clients, servers, and communication protocols. This model is then subjected to formal verification, utilizing techniques like model checking and symbolic execution to identify potential security breaches and inaccuracies. The results demonstrate the feasibility and effectiveness of applying formal verification to FL, offering a robust approach to ensuring the trustworthiness of these systems. Key performance metrics, including privacy loss, communication overhead, and model accuracy deviations, are quantified and analyzed within the verification process. The framework contributes to the development of more reliable and secure FL applications, particularly in sensitive domains such as healthcare and finance.
Nadia Dahmani, Imen Ben Salem, Syed Muhammad Salman Bukhari
Abstract Air quality (AQ) related health risks are increasing globally, creating urgent demand for artificial intelligence (AI) systems that are privacy-preserving, transparent, and auditable. Although Federated Learning (FL), Distributed Ledger Technologies (DLT), and Explainable AI (XAI) are widely recognized as core components of trustworthy AI, existing research remains divided across technical and application domains. This study conducts a computational, multistage systematic review (SR) of scholarly literature records published between 2011 and 2025 using the Semantic Scholar Graph API with intersection and union search strategies. A total of 13,458 records were retrieved and refined into a research-grade corpus of 7,215 publications through DOI-based deduplication, abstract quality diagnostics, venue and publication type screening, and exclusion of non-research artifacts. We used synergy detection, bibliometric analysis, and semantic clustering to study how these technologies are combined and distributed across research domains. The semantic clustering was performed using Sentence-BERT embeddings and UMAP. The results reveal a major structural gap. Among the 6,942 technology-tagged publications in the final 7,215-paper corpus, only 25 studies were identified as triple-synergy candidates that jointly mention or report the combined use of FL, DLT, and XAI, accounting for approximately 0.4%. Among these 25 triple-synergy publications, only two studies (8%) addressed climate or environmental applications, whereas 23 studies (92%) focused on healthcare or general AI. Semantic analysis further categorizes the studies into four areas: environmental sensing, provenance, governance, and clinical risk modeling. This division creates a critical challenge for scalable deployment, cross-domain interoperability, and policy-ready AI systems for AQ-health decision-making. To address this gap, we propose the Green-AI-Trust Stack, a layered architectural framework that integrates three complementary pillars (FL for privacy-preserving distributed learning, DLT for verifiable data and model provenance, and XAI for interpretable inference and decision support within a unified AQI-health pipeline). The findings provide practical direction for researchers, policymakers, and practitioners by identifying key research gaps, methodological needs, and future opportunities for reliable, auditable, and explainable AQI-health AI systems.
This paper proposes a novel decentralized consensus algorithm designed to achieve Byzantine fault tolerance while simultaneously incorporating differential privacy mechanisms. The core idea is to leverage a blockchain-inspired architecture for transaction validation and agreement, enhanced with encrypted transactions and a randomized consensus protocol. Crucially, noise is injected into the consensus process to obscure individual contributions, thereby satisfying differential privacy constraints. The algorithm addresses the critical challenge of combining security and privacy in distributed systems, offering a robust solution for applications requiring both data integrity and user privacy protection. We formally define the algorithm, outlining the key components and their interactions, and analyze its properties regarding fault tolerance, privacy guarantees, and performance. The approach represents a significant step towards practical decentralized systems capable of handling malicious actors while respecting individual user data. The presented framework provides a foundation for future research and development in this increasingly important area.
Federated learning (FL) enables collaborative model training without centralizing raw training records, but it does not inherently provide verifiable model provenance, enforceable fairness policies, or auditable control over aggregation. This paper presents FairAI, a blockchain- and IPFS-enabled framework that treats each local model as a governed artifact linked to performance and group-fairness metrics, content identifiers, manifests, Groth16 evidence, and smart-contract decisions. Only models approved on-chain and subsequently retrieved and validated through their registered CIDs are eligible for aggregation. The primary real-data evaluation used the Adult and COMPAS datasets under IID and joint label/protected-group non-IID partitions, with ten paired seeds comparing standard FedAvg, post hoc fairness assessment, a pre-aggregation fairness policy gate, and FairFed. Under heterogeneous Adult data, the policy gate reduced the demographic-parity gap from 0.0273 to 0.0127, while accuracy decreased from 0.7740 to 0.7629. Under heterogeneous COMPAS data, the equalized-odds gap decreased from 0.2262 to 0.1226, while accuracy decreased from 0.6495 to 0.5809; the paired accuracy and equalized odds differences remained significant after Holm correction, with adjusted p-values of 0.0318 and 0.0491, respectively. Additional bounded experiments evaluated a small multilayer perceptron, policy threshold sensitivity, logical-client scaling, poisoning, coordinate-wise median aggregation, two native Kubo/IPFS peers, V2 Groth16 verification, and smart-contract overhead. Thirty valid V2 proofs were accepted, six inconsistent cases were rejected, and direct Solidity verification consumed 348,811 gas per measured transaction. A full-path false-metric experiment showed that the proof verifies threshold compliance and artifact binding for supplied values, but does not establish their correct derivation from private data. When an approved artifact became unavailable, FairAI cancelled the round before aggregation and published no global model.
Open access
Privacy-Preserving Technologies in Data
Ethics and Social Impacts of AI
Artificial Intelligence in Healthcare and Education
Blockchain-based credential verification provides durable integrity and decentralized validation, but the persistence of blockchain commitments can make premature disclosure of sensitive attributes difficult to reverse. This study developed a pre-commitment privacy risk intelligence framework that assessed potential information leakage before credential commitment and used the estimated risk to guide adaptive protection. Synthetic credential records and simulated attacker-side information were employed to characterize privacy exposure through uniqueness, re-identification susceptibility, cross-source linkage, attribute inference, and attributeinteraction effects. These indicators were transformed into predictive features and evaluated using machinelearning models for continuous privacy-risk estimation and categorical risk assessment, followed by an optimization stage that considered privacy reduction and retained utility. In the reported training experiment, the gradient-boosted regression model achieved a mean absolute error of 0.03290, root mean square error of 0.04645, and coefficient of determination of 0.84398. Logistic regression provided the strongest classification performance, attaining 85.63% accuracy, 81.33% recall, an F1-score of 82.44%, and a privacy false-negative rate of 18.67%. A subsequent evaluation of 1,100 records reduced the mean privacy-risk score from 0.81826 to 0.67337, corresponding to a 17.71% relative reduction, while maintaining a mean utility score of 0.84227. The findings indicated that pre-commitment privacy assessment could support risk-sensitive protection decisions while retaining substantial utility for verifiable credential processing.
Federated learning (FL) has emerged as an important distributed machine learning paradigm allowing many users to train a model together without sharing raw data. However, FL’s decentralized design makes it very susceptible to both Byzantine and coordinated model poisoning attacks, where a few malicious rounds of gradients are strategically inserted to reduce the overall integrity of the model. Even the existing Byzantine-resilient aggregation methods such as geometric median, Krum, and trimmed mean are vulnerable to sophisticated, coordinated poisoning attacks that leverage statistical gaps in outlier detection. In this article, we present FedSentinel, a novel Byzantine-resilient federated learning framework that combines cryptographic gradient attestation with adaptive trust-weighted aggregation to protect against coordinated model-poisoning attacks, which are among the most serious challenges. Three key innovations are introduced in FedSentinel Cryptographic Gradient Attestation Protocol (CGAP) that utilizes commitment schemes and zero-knowledge range proofs to ensure the integrity of the gradients and verify that submitted updates satisfy predefined norm and direction constraints; in the current protocol configuration, CGAP provides gradient integrity verification rather than full gradient confidentiality from the server Dynamic Trust-Weighted Robust Aggregation (DT-RoA): the computation and updating of per-client trust scores based on historical gradient consistency and cross-validation signals; and Coordinated Attack Detection Engine (CADE): based on spectral analysis of the gradient covariance matrices, it detects and isolates colluding Byzantine clients. By participating in up to 100 clients on CIFAR-10, CIFAR-100, FEMNIST, and Sentiment140 datasets, extensive experiments conducted under up to 30% Byzantine adversaries reveal that FedSentinel achieves 91.36% average global accuracy, whereas state-of-the-art defenses such as FLTrust, FLAME, RoFL, ShieldFL, and DnC achieve 83.83–86.94%. FedSentinel outperforms these defenses by 4.42–7.53% in terms of accuracy, while decreasing attack success rates by 53.2% under coordinated Byzantine backdoor attacks. The proposed framework offers a promising approach for federated learning that is verifiable and trustworthy in adversarial environments.
Miriam W. Kaara, Jael S. Wekesa, Michael W. Kimwele
The integrity and credibility of educational institutions worldwide are being undermined by the growing issue of academic certificate fraud. The public's trust in the educational system, the integrity of job opportunities, and the legitimacy of authentic credentials are all negatively impacted by academic dishonesty. The majority of academic credentialing systems, both centralized and blockchain-based, focus on academic credential validation and immutability, even though academic institutions have embraced technology to improve academic credentialing procedures. This suggests that their support for intelligent and private fraud detection is minimal. In this work, we suggest an integrated method that combines smart anomaly detection with Federated Learning (FL). This makes it possible for several organizations to build a model for detecting certificate fraud without disclosing private information to other organizations. Each institution's private information is retained and incorporated into a global model. This enables the framework to handle concerns about data ownership and privacy as well as regulatory compliance. The framework uses Extreme Gradient Boosting (XGBoost) to identify anomalies in metadata and Convolutional Neural Networks (CNNs) to detect visual forgeries in certificates. A decentralized node is used to train the models, which are merged using the Federated Averaging (FedAvg) algorithm. The federated model performs well in anomaly detection, according to the experiments conducted. When compared to conventional centralized approaches, it significantly reduces false positives and false negatives, with an accuracy of up to 94% and an AUC of 0.97. The model's findings imply that a federated learning approach would make it possible for institutions to detect fraud in a secure, scalable, and cooperative manner. In this regard, this framework offers a workable way to create digital credential systems that are more trustworthy and protect privacy. Key words: Federated Learning, Blockchain, certificate fraud detection, privacy preservation, distributed datasets, secure collaboration.
Aasem N. Alyahya, Muidh Awadh Algahtani, Amani Ibraheem, Naglaa F. Soliman · 8 authors
Industry 4.0 is evolving rapidly, 6G networks are emerging, and this has led to a dramatic increase in ultra-latency-critical, computationally demanding jobs in Industrial Internet of Things (IIoT) environments such as real-time digital twins, collaborative robots, and augmented reality-guided assembly. However, the conventional D2D-assisted mobile edge computing (MEC) systems suffer from the severe performance degradation due to the harsh factory propagation environment, severe security threats on the open D2D links, strict industrial data privacy requirements, selfish resource sharing behaviour, and frequent service migration due to device mobility. In this research, we propose a holistic secure task co-offloading system that integrates Reconfigurable Intelligent Surfaces (RIS), permissioned blockchain with smart contracts, and federated learning, into an integrated D2D-MEC architecture for the IIoT. A federated secure multi-armed bandit algorithm enables privacy-preserving decentralized decision-making without revealing sensitive industrial data. Blockchain records off-load transactions through immutable ledgers and enables smart-contract-based incentive enforcement. RIS renders unreliable wireless channels dynamic with minimum energy overhead. In scenarios with hostile and imprecise information, the collaborative design can lower the long-term cost of the system, including task latency, energy consumption, migration overhead, and blockchain transaction fees. The proposed framework, compared to state-of-the-art baselines, reduces the average job completion latency by 29.6%, energy consumption by 36.8%, and migration cost by 41.2%, as demonstrated by extensive trace-driven simulations in actual 6G-IIoT manufacturing scenarios. The experimental results also show the robust performance under the simulated willingness manipulation and poisoned federated updates. The permissioned blockchain architecture provides the architectural security against the Sybil attack and other trust-related threats.