The rapid expansion of the Internet of Things (IoT) has led to unprecedented growth in real-time data generation, and this growth is raising issues concerning data security, privacy, and scalability. Conventional data processing mechanisms based on centralization are confronted with high latency, single points of failure, and vulnerability to cyberattacks. To address such issues, in this study, blockchain and Federated Learning (FL) are being used to implement an end-to-end secure and decentralized system for IoT data analytics in real time. Federated Learning enables IoT devices such as wearable health sensors, industrial sensors, and home automation devices to locally train AI models and transfer model updates rather than raw data and thereby ensure privacy and avoid communication overhead. To ensure security and trustfulness in model updates, a blockchain network using Hyperledger Fabric and Quorum is integrated with FL to avoid tampering and keep the process transparent with a decentralized ledger. Smart contracts are employed to authenticate and aggregate model updates so that only trusted devices can participate in training. Recurrent Neural Networks (RNN), Reinforcement Learning (RL), and Random Forest (RF) models are employed to enhance learning efficiency in the research. A database of 3,450 records is obtained from IoT sensors, and performance is quantified in terms of accuracy in the models, blockchain transaction speed, latency, energy usage, and bandwidth efficiency. The findings show that RNN is 97.86%, RL 93.4%, and RF 90.23%, confirming the success of the proposed system. The research highlights the potential of blockchain-FL integration for privacy-preserving training of AI in large-scale IoT applications, making it relevant to application areas such as healthcare, finance, and industrial automation.
We present Viturka, a blockchain architecture that replaces wasteful proof-of-work mining with productive federated learning. The core innovation is Proof of Credibility (PoC): a consensus mechanism where block production probability is determined by accumulated reputation from validated AI contributions rather than computational hash power or financial stake. Viturka leverages recent breakthroughs in Zero-Knowledge Machine Learning (ZKML) to achieve cryptographic verification of model training. Validators generate zero-knowledge proofs attesting to correct training execution, enabling instant on-chain verification without trusted intermediaries or statistical consensus mechanisms. By integrating frameworks like EZKL and Lagrange's DeepProve with GPU-accelerated proving via the Icicle library, validation that previously required hours of recomputation now produces mathematical proofs verifiable in milliseconds. Participants earn credibility by contributing quality training data or validating others' contributions. Only the top 10 highest-credibility validators can participate in validation rounds, with mandatory cooldown periods ensuring rotation. The system uses a temporal commit-reveal scheme for data contributions combined with ZK proofs for validationâfake contributions result in permanent bans, while fraudulent validation is mathematically impossible. This creates infrastructure for training AI models on distributed data without central coordination, with economic incentives aligned toward data quality rather than raw computation. Applications range from commercially valuable use cases like DeFi credit scoringâwhich could unlock over $100B in overcollateralized capitalâto public-good AI for rare diseases, minority languages, and environmental monitoring.
In order to ensure the transparent and immutable maintenance of healthcare data, Blockchain technology has been proposed, but it places privacy against core requirementsâone of which is privacy demanded by law. Anonymization techniques present today are useful in providing privacy, however they fall short in this sense in terms of guarantee. While zero-knowledge proofs (ZKPs) are one of the strongest cryptographic attestations, they come with hefty computational costs. This paper proposes an HH-ZKP model within a patient-specific-scope and selective disclosure on a smart contract. On a preliminary note, energetic sorting of electronic health records is actually done where anonymization is achieved using hybrid heuristic methods adhering to the constraints of k-anonymity and l-diversity. This is later followed by succinct ZKPs, ensuring that privacy is being obeyed without exposure of any of the hiding values. Again, the aggregations of these proofs are put onto the block with the smart contract, optimized for gas usage, to increase the scalability to a higher level. It is shown through experimental evaluations on the 10 K synthetic EHR dataset that the proposed scheme shows about a 75% reduced on-chain cost four times reduced proof sizes fully meeting HIPAA Safe Harbor compliance. The HH-ZKP model, by yielding a hybrid of heuristic-preprocessing and formal-principled cryptographic verification, is paving the way for scalable and regulator-aware blockchain health applications.
Guilhem Repetto, Nojan Sheybani, Gabrielle De Micheli, Farinaz Koushanfar
Privacy concerns in machine learning systems have grown significantly with the increasing reliance on sensitive user data for training large-scale models. This paper introduces a novel framework combining Probably Approximately Correct (PAC) Privacy with zero-knowledge proofs (ZKPs) to provide verifiable privacy guarantees in trustless computing environments. Our approach addresses the limitations of traditional privacy-preserving techniques by enabling users to verify both the correctness of computations and the proper application of privacy-preserving noise, particularly in cloud-based systems. We leverage non-interactive ZKP schemes to generate proofs that attest to the correct implementation of PAC privacy mechanisms while maintaining the confidentiality of proprietary systems. Our results demonstrate the feasibility of achieving verifiable PAC privacy in outsourced computation, offering a practical solution for maintaining trust in privacy-preserving machine learning and database systems while ensuring computational integrity.
This paper addresses the technical and regulatory challenges of building secure data pipelines to support federated learning (FL), where models train collaboratively across multiple organizations without sharing raw data. The paper explores privacy-preserving data engineering techniques such as differential privacy, homomorphic encryption, and secure aggregation within ETL frameworks. It outlines an architecture for orchestrating decentralized dataflows that comply with GDPR, HIPAA, and other regulatory standards while enabling cross-institutional AI innovation. By integrating secure connectors, encrypted model updates, and audit logging, the proposed pipeline design ensures both data protection and analytic utility, providing a blueprint for responsible AI deployment in healthcare, finance, and government sectors.
The fifth-generation (5G) networks are facing critical security challenges in device authenti- cation for massive Internet of Things deployments while preserving privacy. Traditional federated learning approaches depend on the computationally expensive homomorphic encryption to protect model gradients, resulting in substantial latency, communication over- head, and the energy consumption impractical for resource-constrained 5G devices. This paper proposes zero-knowledge federated learning (ZK-FL), eliminating homomorphic encryption by enabling devices to prove model correctness without revealing gradients. Our approach integrates zero-knowledge proofs with FL updates, where each device generates where each device generates a proof Proofi = ZK(Gradienti, Hashi), demon- strating computational integrity.Experimental results from 10,000 authentication attempts demonstrate ZK-FL achieves 78.4 ms average authentication latency versus 342.5 ms for homomorphic encryption-based FL (77% reduction), proof sizes of 0.128 KB versus 512 KB (99.97% reduction), and energy consumption of 284.5 mJ versus 6.525 mJ (95% reduc- tion), while maintaining 99.3% authentication success rate with formal privacy guarantees. These results demonstrate ZK-FL enables practical privacy-preserving authentication for massive-scale 5G deployment.
Background Cross-domain federated learning is an innovative machine learning paradigm that allows data owners from different domains to collaboratively train a shared model while preserving data privacy. However, cross-domain federated learning also faces numerous challenges, such as data and system heterogeneity, client reputation management, and potential threats from malicious attackers. Methods To address these issues, this article proposes a secure cross-domain federated learning scheme based on blockchain fair payment. The proposed scheme effectively evaluates and updates the reputation of each client through a reputation management mechanism and allocates fair rewards based on their contributions. Additionally, the scheme employs advanced cryptographic technologies such as blockchain and zero-knowledge proofs to ensure the security and fairness of data and transactions. A series of experiments are conducted to evaluate the performance and fairness of the proposed scheme on multiple datasets and models, and comparisons are conducted with other mainstream federated learning algorithms. MNIST Dataset is available at: https://www.kaggle.com/datasets/hojjatk/mnist-dataset . Fashion-MNIST Dataset is available at https://github.com/zalandoresearch/fashion-mnist . CIFAR-10 Dataset is available at https://www.cs.toronto.edu/~kriz/cifar.html . Results The experimental results demonstrate that the proposed scheme ensures the performance of federated learning while also maintaining its fairness and security. Specifically, the method achieves a test accuracy of 97% on the MNIST dataset, outperforming Federated Averaging (FedAvg) (95%) and Stochastic Controlled Averaging for Federated Learning (SCAFFOLD) (96%). On the FEMNIST dataset, it attains 89% accuracy. In terms of convergence speed, the proposed optimization-based reputation method converges in 26 rounds, which is faster than baseline methods (28â32 rounds). Under data tampering attacks (50-client scenario), the accuracy drop is less than 3%, showing strong robustness. For fairness, the trust difference and reward difference are reduced to 0.10 and 0.08, respectively. The proposed scheme significantly improves the accuracy, convergence speed, robustness, and fairness of cross-domain federated learning, advancing its practical deployment in real-world scenarios. The experimental data is available at: https://zenodo.org/records/15210778 .
Gradient boosted decision trees, particularly XGBoost, are among the most effective methods for tabular data. As deployment in sensitive settings increases, cryptographic guarantees of model integrity become essential. We present ZKBoost, the first zero-knowledge proof of training (zkPoT) protocol for XGBoost, enabling model owners to prove correct training on a committed dataset without revealing data or model parameters. Naively re-executing XGBoost training in ZK would incur prohibitive costs, primarily due to the oblivious partitioning of training samples and unknown tree splits. Moreover, previous work on ZKP of training and inference had subtle security issues, such as leakage of tree topology and soundness gaps allowing cheating model providers to deviate from the correct execution of training and inference. We make two key contributions to address these challenges: (1) a generic zkPoT template for XGBoost that can be instantiated with any general-purpose ZKP backend, significantly improving prover costs compared to naive re-execution of the training process; and (2) a VOLE-based instantiation that overcomes the security issues of previous ZK proofs of training at minimal costs. To maximize efficiency, we develop a fixed-point version of XGBoost, which is particularly well suited for efficient instantiation of ZKP, and show it matches standard XGBoost accuracy to within 1\% on real-world datasets.
ABSTRACT To address the challenges of coarseâgrained access control, collusion attack risks, and massive data storage issues in crossâdepartmental traffic data sharing within Intelligent Transportation Systems (ITS) scenarios, this study proposes an AttributeâBased Conditional Proxy ReâEncryption (ABâCPRE) scheme integrated with blockchain technology. This scheme employs a conditional proxy reâencryption mechanism to achieve fineâgrained access control based on device attributes and access policies, thereby defending against collusion attacks by proxy nodes and malicious users. By combining the distributed ledger of blockchain and IPFS's distributed storage of IPFS, a verifiable system is constructed that includes ciphertext hashes, a complete set of device attributes, and operational conditions. This ensures data integrity while reducing the computational and storage pressure on edge servers. Security analysis demonstrates that the scheme satisfies adaptive INDâCCA security under the standard model, and performance evaluation indicates significant improvements in computational efficiency and communication overhead compared with similar schemes.
Modern cryptographic primitives have evolved from supporting basic to more advanced functionalities, and such schemes are now getting more practical. In this thesis, we identify and rectify some limitations of such cryptographic constructions and their proofs of security. Specifically, we work with functional encryption, secure aggregation, and threshold signature schemes, and observe key functional or security limitations in prior work. Our first focus is functional encryption (FE), which enables function evaluation on encrypted messages using a functional secret key. A different primitive named function-revealing encryption (FRE) allows one to compute a fixed function of the underlying messages using their ciphertexts only. We give formal definitions and construct an inner-product FRE scheme. We also analyze the relationship between FE and FRE. Our second contribution considers secure aggregation, a classic problem that has numerous applications in privacy preserving machine learning. Secure aggregation lets many clients contribute data for aggregation without revealing their individual data. Existing practical protocols either have multiple rounds of interaction between clients and the server or rely on heavyweight cryptographic primitives. We build a non-interactive secure aggregation protocol using a novel combination of inner-product FE and a fully-linear probabilistically checkable proof (FLPCP) system. For this protocol, we use an existing FLPCP system [BBCGIâ19] that we prove satisfies soundness and zero-knowledge properties even when reused for multiple proof instances. Finally, we address a pressing open question: achieving fully adaptive security for the Sparkle+ [CKMâ23] threshold signature scheme. Threshold schemes require t signers to provide partial signatures to form a valid one. Fully adaptive security prevents adversaries from forging signatures even when corrupting up to t-1 signers. While Sparkle+ is secure against static corruption and a limited number of adaptive corruptions, a previous proof of fully adaptive security was shown to be incorrect. We propose a novel hardness assumption under which Sparkle+ satisfies this notion with a tight reduction. We establish hardness of this assumption in the elliptic-curve generic-group model. Our contributions close important gaps in prior work and push advanced cryptographic primitives closer to practice.
This study presents HoloCyberChain, an entropy-driven blockchain framework for decentralized cyber-threat intelligence with formal verification and privacy preservation. Each cyber event is encoded as a four-dimensional entropy fingerprint capturing structural, temporal, behavioral, and propagation uncertainty. A novel Shannonâβ hybrid distance integrates residual-entropy geometry with β-divergence-based distributional separation, yielding a unified statisticalâtopological measure of threat dissimilarity. Residuals are transformed into calibrated novelty probabilities through a logistic uniqueness gate, while a proof-of-detection consensus protocol enables publicly verifiable and Byzantine-resilient acceptance of novel intelligence. Privacy is maintained using zero-knowledge entropy proofs, and accepted threats are organized into a spectral threat-intelligence graph that preserves family-level separability. Simulation experiments demonstrate reliable discrimination (ROC-AUC â0.81, PR-AUC â0.77) and stable calibration under noise and concept drift. Real-world validation using the CICIDS-2017 dataset (225 745 flows, 79 features; 97 718 benign and 128 027 DDoS flows) confirms that DDoS traffic exhibits higher Shannonâβ entropy, with right-shifted density profiles, higher medians, and tighter interquartile ranges relative to benign traffic, indicating that the proposed entropy formulation preserves separability under realistic traffic imbalance. These empirical results align with theoretical guarantees and simulation findings, establishing HoloCyberChain as a reproducible, entropy-verified foundation for scalable and privacy-preserving cyber-threat intelligence sharing.
Syed Raza Abbas, Zeeshan Abbas, Mobeen Ur Rehman, Seung Won Lee
Background Blockchain is increasingly explored as an infrastructure to mitigate data fragmentation, security incidents, and limited patient control in digital health ecosystems. This systematic review analyzed applications of blockchain in smart health systems, with a focus on security models, interoperability approaches, and integration with Internet of Things (IoT) and artificial intelligence (AI). Methods Following PRISMA 2020, PubMed, IEEE Xplore, ScienceDirect, Springer, and Google Scholar were searched for studies published between January 2019 and August 2025 using a predefined strategy combining the terms (âblockchainâ OR âdistributed ledgerâ) AND (âhealthcareâ OR âmedicalâ OR âhealth recordsâ) AND (âsecurityâ OR âprivacyâ OR âinteroperabilityâ); of the 1847 records screened, 26 studies met the eligibility criteria. Results Across these studies, blockchain most consistently strengthened electronic health record management by providing cryptographic access control, tamper-evident and immutable audit trails, and support for cross-institutional data exchange. In four multi-institutional settings, coupling blockchain with AI enabled privacy-preserving federated learning for collaborative diagnostics without centralized data pooling. However, several technical and regulatory constraints were reported, including limited scalability (median throughput <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline" overflow="scroll"> <mml:mo>â</mml:mo> </mml:math> 850 transactions/second vs. >10,000/seconds typically required for national infrastructures), high energy consumption in proof-of-work based schemes, and unresolved tension between immutable ledger storage and data protection rules such as the General Data Protection Regulation âright to be forgotten.â Conclusion Overall, the evidence indicates that blockchain is a credible enabler of secure, interoperable, and patient-governed health data sharing, provided that future deployments incorporate Layer-2 or comparable scalability mechanisms, adopt energy-efficient consensus protocols, and operate within clearer regulatory guidance on the permanence of clinical data.
Centralized e-commerce recommenders face privacy risks, while Federated Recommendation Systems (FRS) suffer from accuracy loss in sparse environments and rely on untrusted aggregators. We propose BL-ZPRS, a framework utilizing bilayer zk-SNARKs for end-to-end trustworthiness. Its lower-layer User-to-Anchor (U2A) paradigm restores collaborative signals via verifiable vectors without exposing raw data, while an upper-layer ZKP proves FedAvg integrity. Evaluations on the Amazon Review dataset show BL-ZPRS achieves accuracy comparable to centralized models with superior resistance to poisoning attacks, effectively balancing privacy and integrity.
In digital security, anonymous credential systems are essential to ensure secure and private interactions. These systems have practical applications in various fields, such as online voting, healthcare, and financial services. However, due to high computational overhead and complex architecture, traditional anonymous credential systems often suffer from efficiency and scalability issues. To address these challenges, we propose an innovative approach that combines advanced cryptographic techniques such as randomized BLS aggregate signatures and optimized zero-knowledge proof usage mechanisms to achieve secure and private identity authentication with minimal overhead. We introduce HPPCS (High-Performance Privacy-Preserving Credential System), an anonymous credential framework that leverages randomizable aggregate signature technology to achieve efficiency and strong security. We conducted a security and experimental analysis of the HPPCS framework, and the results showed that HPPCS improves the efficiency of credential generation and verification while ensuring original security. This work establishes a powerful and practical framework for privacy-centric identity authentication systems.
The rapid proliferation of smart home IoT devices has introduced unprecedented cybersecurity vulnerabilities, necessitating scalable and privacy-preserving intrusion detection systems (IDS). Federated Learning (FL) offers a promising decentralized approach by training models locally without sharing raw data, but it remains susceptible to poisoning attacks and relies on a vulnerable central aggregator. This paper presents a novel blockchain-enhanced FL framework tailored for smart home IDS, integrating multiple consensus mechanismsâProof-of-Stake (PoS), Practical Byzantine Fault Tolerance (PBFT), and Proof-of-Authority (PoA)âfor the first time in this context. Our approach uniquely combines differential privacy (DP) and secure aggregation (SA) within a blockchain-managed workflow to mitigate gradient inversion and membership inference attacks while ensuring tamper-resistant, decentralized trust. Experimental evaluation using the N-BaIoT dataset demonstrates that the proposed system achieves up to 88.3% detection accuracy with manageable latency (~200 ms/round) and formal privacy guarantees ($\varepsilon$=1.0 DP). The framework introduces 52.8% system overhead compared to vanilla FLâa reasonable trade-off for enhanced security and privacy. This work establishes a robust, transparent, and scalable security infrastructure for smart homes, effectively addressing the limitations of both centralized and conventional FL-based IDS.
Abstract With the growing implementation of multi sensor Internet of Things (IoT) and edge AI systems, the concerns over data reliability,privacy, and verifiability have been intensified. Conventional fusion architectures rely on deep learning models that deliverhigh accuracy. However, they fail to ensure that inferences are provably correct or tamper resistant under missing, noisy, oradversarial data conditions. To address these challenges, this paper introduces the Zero-Knowledge Privacy Assured SensorFusion (ZK-PAS Fusion) framework. ZK-PAS Fusion integrates convex bounded imputation, attention driven multi sensorfusion, BiLSTM based temporal modeling, and recursive zero-knowledge proof aggregation within a unified architecture. Theframework assures correctness, privacy, and robustness through cryptographic commitments and circuit level verifiability.Experimental evaluation is performed on two large scale clinical datasets, namely, MIMIC-IV and eICU-CDR. The modeldemonstrates a superior performance and achieves 99.45 % accuracy, 99.57 % F1-score, and an AUROC of 0.989, surpassingstate of the art transformer and diffusion based baselines by up to 5.4 % in accuracy and 6.2 % in F1-score. The proof moduleattains a 40 ms average proving time, 0.4 KB proof size, and â 46 % lower energy consumption compared to state of the art(SOTA) models. These results establish ZK-PAS Fusion as a verifiable, memory efficient, and privacy preserving AI frameworkfor real time, safety critical edge IoT deployments.
This deliverable (D4.4 â Federated AI/ML) defines the architecture, requirements, and enabling technologies for secure and privacy-preserving federated learning within the CONFIDENTIAL6G project. The document specifies how federated AI/ML can be safely deployed across heterogeneous 6G cloudâedge environments, allowing collaborative model training while ensuring that sensitive data remains local and protected throughout the learning lifecycle. The deliverable consolidates background and state-of-the-art insights on federated learning in 6G, identifies key security, privacy, and trust challenges, and derives a set of functional, security, governance, and operational requirements that guide system design. It then presents the overall federated AI/ML architecture developed under this task, which brings together confidential orchestration, federated learning coordination, cryptographic trust mechanisms, and secure execution across cloud-edge environments. The architecture builds on the confidential orchestration foundations established in Deliverable 4.3 and integrates key enablers from WP2âsuch as Decentralized Identifiers, Verifiable Credentials, and Zero-Knowledge Proofsâto support verifiable, policy-driven, and privacy-preserving participation throughout the federated learning lifecycle. Within this architecture, blockchain-enabled aggregation is introduced as a complementary mechanism to strengthen integrity, auditability, and decentralized trust in model management and aggregation workflows by removing single points of failure and providing tamper-evident provenance for AI/ML models. In parallel, the deliverable reports algorithmic contributions that enhance robustness and fairness under non-IID data distributions and device heterogeneity, ensuring that the proposed architecture remains effective under realistic deployment conditions. Finally, the document outlines how the Federated AI/ML integrates with WP5 use cases, demonstrating its relevance for real-world validation scenarios. Overall, this deliverable establishes a coherent and secure federated learning foundation that supports CONFIDENTIAL6Gâs objectives for trustworthy, privacy-preserving AI in next-generation 6G environments.
We present Y.I.N.-MEMORIA, a comprehensive privacy-preserving architecture addressing fundamental vulnerabilities in AI conversation systems across all platforms, including large language model interfaces, enterprise AI assistants, domain-specific chatbots, and agentic AI systems. The system implements mandatory cryptographic ordering enforcement (DP â ZK â BLINDING â HE, or functional equivalents), mathematically proven unique among 24 permutations, achieving 99.37% accuracy for valid authorizations versus 50.7% for invalid attempts (t = 147.3, p < 10âťâľâ°). KEY CONTRIBUTIONS:⢠Hybrid local-cloud storage with zero-knowledge properties ensuring cloud providers mathematically cannot decrypt conversations⢠Enterprise Shadow AI governance achieving 99.7% detection across 50+ services via network pattern analysis without plaintext access⢠Y.A.N.G. constant-time retrieval providing 340Ă timing attack resistance (reduced leakage from 2.72 to 0.008 bits per 1,000 queries)⢠Complete defense taxonomy across 8 attack categories with quantified metrics (92-99% detection rates)⢠Advanced cryptographic primitives including post-quantum aggregate signatures (90% size reduction), threshold token generation, VRFs, adaptive differential privacy (4-tier Îľ system), federated unlearning (SISA), and incremental Merkle tree encryption⢠Four complete deployment architectures (cloud-only, local-only, mobile-only, enterprise gateway) validated across 4 hardware platforms and 5 operating systems⢠Y.I.N. CERTIFY compliance verification layer enabling machine-readable regulatory certificates for GDPR, DORA, EU AI Act, HIPAA, and Singapore's Model AI Governance Framework for Agentic AI⢠Synergistic combination claims and negative exclusion claims establishing comprehensive defensive prior art ENHANCED VERSION 10.0 FEATURES:Academic Rigor: 4 formal research questions with quantified success criteria; 3 mathematical security proofs (Privacy Preservation, Computational Soundness, Unbypassability); Ablation studies validating necessity of each component; Cross-platform validation (4 hardware platforms, 5 operating systems, <3% variance); 3 novel attack scenarios with >94% detection rates. Comparative Analysis: Table comparing against 8 major systems (Federated Learning, CrypTen, TF Privacy, Opacus, PySyft, Microsoft SEAL, Zcash). Y.I.N.-MEMORIA demonstrated as only system providing mandatory DP enforcement, ZK verification for AI governance, 340Ă timing resistance, 99.7% Shadow AI detection, and complete lifecycle coverage. Legal Protection: Doctrine of equivalents coverage (Warner-Jenkinson precedent); Willful infringement notice (Halo Electronics, 3Ă damages); Comprehensive functional equivalents (12 categories); Minimum performance thresholds excluding weak implementations. Reproducibility Commitment: Complete reference implementation under open-source license; Experimental datasets via Zenodo; Cryptographic test vectors for independent verification; Performance benchmarks across all platforms. Scholarly Depth: 38 peer-reviewed citations (65% increase); Comprehensive related work analysis; Explicit limitations and future research directions; Historical non-obviousness evidence. THREE-PHASE AI LIFECYCLE COVERAGE:Y.I.N.-MEMORIA completes the Y.I.N. Architecture's three-phase AI lifecycle: Training (Y.I.N.-LLM, USPTO 63/941,283), Generation (Article 50 Compliance Engine, USPTO 63/957,571), and Usage (Y.I.N.-MEMORIA, USPTO 63/967,805). The Y.I.N. CERTIFY verification layer spans all three phases. Together, these components provide 643 total claims covering every stage where privacy vulnerabilities can emerge in AI systems. EXPERIMENTAL VALIDATION:85-95% bandwidth reduction, 97% conflict resolution, and compliance scores of 94.7-97.3% for GDPR, HIPAA, DORA, EU AI Act, Singapore MGF for Agentic AI, ISO/IEC 42001, CCPA, and NIS2 Directive. IMPACT METRICS:This architecture prevents Shadow AI breaches costing $4.63M average (20% of all data breaches according to IBM's 2025 Cost of a Data Breach Report), addresses the 20M ChatGPT conversation log discovery precedent (NYT v. OpenAI, January 2026), and satisfies Singapore's Model AI Governance Framework for Agentic AIâthe world's first comprehensive government framework for autonomous agents published January 22, 2026 (4 days prior to this work). DEFENSIVE PRIOR ART:This work establishes comprehensive prior art corresponding to USPTO Provisional Application 63/967,805 (438 claims filed January 25, 2026), part of the Y.I.N. Architecture Portfolio (22 applications, 1,360+ total claims). Includes explicit functional equivalents coverage, doctrine of equivalents, and willful infringement notice enabling enhanced damages up to 3Ă under Halo Electronics precedent. Patent Reference: USPTO Application 63/967,805 (Y.I.N.-MEMORIA) License: CC BY-NC-ND 4.0Corresponding Author: ilyesmazari@hotmail.comVersion: 1.0Publication Date: January 26, 2026
Smart mobility services generate large volumes of sensitive location and identity data, raising critical concerns related to privacy leakage, âsecurity vulnerabilities, and trust in large-scale urban deployments. To address these challenges, this paper proposes a blockchain-based âprivacy-preserving framework for smart mobility services that integrates geo-indistinguishability, pseudonymous authentication, Zero-âKnowledge Proofs (ZKPs), and Proof-of-Authority (PoA) consensus into a unified architecture. The framework ensures end-to-end privacy âby combining calibrated location obfuscation with decentralized transaction validation and immutable auditability, thereby mitigating both âinference-based attacks and reliance on centralized trust.â The proposed framework was evaluated using the TAPAS Cologne mobility dataset, comprising 1,000 simulated vehicles and 20 block-âchain validators. Experimental results demonstrate that adversarial inference accuracy is reduced to below 12%, while approximately 75% ânavigation utility is preserved at balanced privacy budgets. Security analysis confirms robust protection against tracking, replay, Sybil, and âcollusion attacks, with replay attack success rates reduced from 70% to 2% through the enforcement of timestamps and nonces, along with âcryptographic verification.â Performance evaluation demonstrates that the framework achieves high throughput (1,200 transactions per second) with sub-second latency ââ(0.8 seconds) under realistic transaction loads. Storage growth is optimized to 2.1 GB per million transactions, and the PoA consensus âmechanism achieves approximately 30% lower energy consumption compared to Proof-of-Stake-based designs. In addition, resilience ex-âperiments confirm Byzantine fault tolerance under up to 30% malicious validator participation, without service degradation.â Overall, the results demonstrate the practical feasibility of deploying the proposed framework in real-world smart mobility ecosystems that ârequire simultaneous privacy preservation, scalability, and energy efficiency. The framework represents a significant step toward trustwor-âthy, privacy-aware, and sustainable smart-city mobility infrastructure, providing a robust foundation for next-generation decentralized mo-âbility servicesâ.
Abstract Healthcare Internet of Things (HIoT) has revolutionized patient care through continuous monitoring and personalized treatment, but it introduces critical challenges in privacy protection, data security, and resource management across heterogeneous devices. Traditional centralized machine learning (ML) approaches face significant limitations due to privacy regulations and security concerns, leading to the emergence of federated learning (FL) and blockchain (BC) as complementary solutions. While FL enables collaborative model training without sharing raw data, and BC provides immutable verification and secure record management. We present SHIELD-Health, a novel framework that synergistically integrates these technologies to create a comprehensive solution for secure analytics in healthcare environments, featuring four key innovations: (1) resource-aware computation that dynamically adapts to device capabilities (2) a multi-layered privacy architecture designed for differential privacy and secure aggregation (3) Byzantine-robust aggregation ensuring model integrity under adversarial conditions, and (4) healthcare-specific optimizations including temporal attention mechanisms for physiological time-series data. Extensive evaluation demonstrates exceptional performance across multiple dimensions, maintaining high accuracy while achieving substantial communication efficiency and energy savings for resource-constrained devices. The framework also shows remarkable resilience against poisoning attacks, and robust performance under challenging non-independent and identically distributed (IID) data distributions common in healthcare scenarios. It represents a significant advancement in privacy-preserving collaborative analytics for sensitive medical applications where security, privacy, and resource constraints are paramount considerations.
Mohammad Shahid, Paritosh Ramanan, Mohammad Fili, Guiping Hu ¡ 5 authors
Analysis of clinical data is a cornerstone of biomedical research with applications in areas such as genomic testing and response characterization of therapeutic drugs. Maintaining strict privacy controls is essential because such data typically contains personally identifiable health information of patients. At the same time, regulatory compliance often requires study managers to demonstrate the integrity and authenticity of participant data used in analyses. Balancing these competing requirements of privacy preservation and verifiable accountability remains a critical challenge. In this paper, we present CoSMeTIC, a zero-knowledge computational framework that proposes computational Sparse Merkle Trees (SMTs) as a means to generate verifiable inclusion and exclusion proofs for individual participants' data in clinical studies. We formally analyze the zero-knowledge properties of CoSMeTIC and evaluate its computational efficiency through extensive experiments. We demonstrate the framework on Huntington's disease and HIV-1 case studies, using simulated CAG-repeat cohorts derived from published summary statistics and published de-identified clinical lab measurements of virus samples. Using two-sample Kolmogorov-Smirnov and likelihood-ratio hypothesis tests, along with logistic-regression-based genomic analyses on the de-identified datasets, we show that CoSMeTIC achieves strong privacy guarantees while maintaining statistical fidelity. Our results suggest that CoSMeTIC provides a scalable and practical alternative for achieving regulatory compliance with rigorous privacy protection in large-scale clinical research.