Federated learning represents a paradigm shift in distributed machine learning by enabling collaborative model training across decentralized nodes while maintaining data privacy at source locations. It helps bridge the gap between artificial intelligence-driven development guidelines and the regulatory mandates laid down by data protection legislation. A decentralized architecture transmits only the model updates to aggregation servers; this reduces privacy breach exposure and compliance violation risks and also eliminates raw data centralization. Federated learning helps build production-ready systems across healthcare, finance, and edge computing environments, owing to the maturities that have occurred in cloud infrastructure. This is a transition from the erstwhile theoretical frameworks it used to have. Architectural advantages are supplemented by privacy-preserving mechanisms like differential privacy and secure aggregation protocols, which facilitate organizations to leverage collective intelligence without exposing sensitive information. Robust platforms for privacy-critical applications can be synthesized by the integration of cloud-native security services, cryptographic enhancements, and edge computing optimization. Courtesy of emerging solutions that cater to model fairness, communication efficiency, and data heterogeneity, federated learning's practical applicability across diverse organizational contexts and regulatory domains continues to advance.
Peer-discovery protocols within P2P networks are often vulnerable: because creating network identities is essentially free, adversaries can eclipse honest nodes or partition the overlay. This threat is especially acute for blockchains, whose security depends on resilient peer connectivity. We present AetherWeave, a stake-backed peer-discovery protocol that ties network participation to deposited stake, raising the cost of large-scale attacks. We prove that, with high probability, either the honest overlay remains connected or a $(1{-}δ)$-fraction of nodes in every smaller component raise an attack-detection flag -- even against a very powerful adversary. To our knowledge, AetherWeave is the first peer-discovery protocol to simultaneously provide Sybil resistance and privacy: nodes prove they hold valid stake without revealing which deposit they own, and gossiping does not expose peer-table contents. A cryptographic commitment scheme rate-limits discovery requests per round; exceeding the limit yields a publicly verifiable misbehavior proof that triggers on-chain slashing. Beyond deposit and slashing, the protocol requires no on-chain interaction, with per-node communication scaling as $O(s\sqrt{n})$. We validate our design through a mean-field analysis with closed-form convergence bounds, extensive adversarial simulations, and an end-to-end prototype built by forking Prysm, a leading Ethereum consensus client.
Privacy-preserving aggregation is a cornerstone for AI systems that learn from distributed data without exposing individual records, especially in federated learning and telemetry. Existing two-server protocols (e.g., Prio and successors) set a practical baseline by validating inputs while preventing any single party from learning users' values, but they impose symmetric costs on both servers and communication that scales with the per-client input dimension $L$. Modern learning tasks routinely involve dimensionalities $L$ in the tens to hundreds of millions of model parameters. We present TAPAS, a two-server asymmetric private aggregation scheme that addresses these limitations along four dimensions: (i) no trusted setup or preprocessing, (ii) server-side communication that is independent of $L$ (iii) post-quantum security based solely on standard lattice assumptions (LWE, SIS), and (iv) stronger robustness with identifiable abort and full malicious security for the servers. A key design choice is intentional asymmetry: one server bears the $O(L)$ aggregation and verification work, while the other operates as a lightweight facilitator with computation independent of $L$. This reduces total cost, enables the secondary server to run on commodity hardware, and strengthens the non-collusion assumption of the servers. One of our main contributions is a suite of new and efficient lattice-based zero-knowledge proofs; to our knowledge, we are the first to establish privacy and correctness with identifiable abort in the two-server setting.
Abdullah Melhem, Ahmed Aleroud, Abdullah Al-Mamun, Mohamed I. Ibrahem · 5 authors
The use of web-enabled healthcare analytics has broadened access to machine learning (ML)- and AI-driven cloud models, but it has also created privacy and security challenges. Federated learning (FL) has been used to address data privacy issues; however, deployments of current FL architectures rely on centralized aggregation approaches, thereby creating a single point of failure (SPoF), as a successful adversarial attack on the global model during training or inference can compromise the entire system. These approaches also assume homogeneous data distributions across clients and overlook the constraints and diversity of web-based analytics. To address those limitations, traditional blockchain-based FL systems incorporated distributed ledgers to record model updates and artifacts. However, using the chain as a data ledger to record model artifacts and logs increases consensus overhead and coordination costs. This paper introduces Blockchain-based Clustered Federated Learning (BCFL), an architecture-diverse and cluster-based FL framework. Our approach is coordinated by a lightweight permissioned ledger that eliminates the trusted central aggregator while preserving utility, robustness, and verifiable provenance in web-based healthcare analytics. BCFL records compact provenance metadata on-chain while keeping model parameters off-chain. In addition, by distributing trust across clusters, the design reduces the transfer of adversarial attacks across models by limiting the impact of malicious updates during training and improving reliability at inference time. Experiments on real-world healthcare data and other benchmarks show that BCFL improves the performance of trained AI/ML models and reduces attack success rates compared with several FL baselines.
Jiayong Chai, Mo Chen, Wei Zhang, Xiaojuan Wang · 5 authors
Cross-domain data collaboration is a core requirement for the intelligent development of critical areas such as the Internet of Vehicles and intelligent transportation systems. In this scenario, vehicles and various sensors deployed roadside continuously generate massive amounts of time-series data, yet this data often forms "data silos" due to privacy regulations and a lack of trust between collaborating entities. Existing integrated schemes combining "Federated Learning + Blockchain" have achieved a certain degree of process traceability and automated payments, but risks of gradient-level privacy leakage persist, and inflexible and delayed incentive mechanisms result in low participation quality. To systematically address these bottlenecks, this paper proposes the Federated Learning with Assured Privacy and Reputation-Driven Incentives (FLARE) architecture, whose core innovation lies in the native integration of cryptographic security and mechanism design theory. It includes the Secure and Faithfully Executed Gradient aggregation (SafeGrad) protocol, which integrates partial homomorphic encryption and zero-knowledge proofs to provide verifiable privacy guarantees for gradient contributions while enabling efficient secure aggregation, defending against inversion attacks at the source; alongside this, it includes the Economy-on-Chain incentive (EconChain) mechanism, which designs an on-chain economic system based on blockchain, achieving precise measurement and sustainable incentivization of training process contributions through fine-grained instant micro-rewards and a dynamic reputation model. Experiments show that, compared to baseline schemes, FLARE can effectively enhance node participation enthusiasm and contribution quality without compromising model accuracy, providing a new paradigm with both strong security and high vitality for the trusted and efficient circulation of data.
Federated learning enables financial institutions to collaboratively develop credit risk models while maintaining data privacy, yet existing implementations prioritize accuracy and confidentiality over transparency and regulatory compliance requirements. Current federated approaches treat explainability as a secondary concern addressed through separate post-processing workflows, creating significant gaps in auditability and stakeholder trust that limit adoption in regulated environments. This article introduces the Explainable Update Auditing framework, which embeds transparency mechanisms directly into federated training protocols through local explanation bundles and privacy-preserving audit trails. The framework generates standardized, model-agnostic explanations that characterize how institutional updates influence global model behavior without exposing proprietary data or competitive information. Cryptographic attestation mechanisms verify compliance with fairness, stability, and governance constraints throughout training processes using zero-knowledge proof systems that maintain institutional confidentiality while providing mathematical assurance of appropriate collaborative behavior. The dual-layer trust mechanism addresses distinct information needs across multiple stakeholder groups, including participating institutions, regulatory authorities, internal governance bodies, and affected borrowers. Implementation considerations reveal computational overhead challenges, privacy-utility trade-offs, and cryptographic protocol efficiency requirements that must be addressed for practical deployment. The framework transforms federated learning from an opaque collaboration protocol into a transparent, auditable ecosystem that satisfies regulatory requirements while preserving privacy guarantees essential for cross-institutional partnerships in credit risk modeling applications.
Federated Learning (FL) enables collaborative training of medical AI models across hospitals without centralizing patient data. However, the exchange of model updates exposes critical vulnerabilities: gradient inversion attacks can reconstruct patient information, Byzantine clients can poison the global model, and the \emph{Harvest Now, Decrypt Later} (HNDL) threat renders today's encrypted traffic vulnerable to future quantum adversaries.We introduce \textbf{ZKFL-PQ} (\emph{Zero-Knowledge Federated Learning, Post-Quantum}), a three-tiered cryptographic protocol that hybridizes (i) ML-KEM (FIPS~203) for quantum-resistant key encapsulation, (ii) lattice-based Zero-Knowledge Proofs for verifiable \emph{norm-constrained} gradient integrity, and (iii) BFV homomorphic encryption for privacy-preserving aggregation. We formalize the security model and prove correctness and zero-knowledge properties under the Module-LWE, Ring-LWE, and SIS assumptions \emph{in the classical random oracle model}. We evaluate ZKFL-PQ on synthetic medical imaging data across 5 federated clients over 10 training rounds. Our protocol achieves \textbf{100\% rejection of norm-violating updates} while maintaining model accuracy at 100\%, compared to a catastrophic drop to 23\% under standard FL. The computational overhead (factor $\sim$20$\times$) is analyzed and shown to be compatible with clinical research workflows operating on daily or weekly training cycles. We emphasize that the current defense guarantees rejection of large-norm malicious updates; robustness against subtle low-norm or directional poisoning remains future work.
Global disruptions, such as the COVID-19 pandemic, have exposed the fragility of supply chains and the critical need for coordination. However, effective collaboration is often hindered by the reluctance of firms to disclose sensitive proprietary data, such as inventory levels or logistical bottlenecks, due to competitive concerns. To resolve this dilemma, this study introduces a privacy-preserving framework integrating Zero-Knowledge Proofs (ZKPs) with blockchain technology. This approach allows stakeholders to validate compliance and operational status without revealing the underlying raw data, thereby fostering trust and resilience in decentralized networks.
Federated learning (FL) enables collaborative model training over distributed private data. However, sustaining open participation requires incentive mechanisms that compensate contributors for their resources and risks. Enabled by Web3 primitives, especially blockchains, recent FL proposals incorporate incentive mechanisms for open participation, yet most focus primarily on algorithmic design and overlook system-level challenges, including coordination efficiency, secure handling of model updates, and practical usability. We present FWeb3, a practical Web3-enabled FL framework for incentive-aware training in open environments. FWeb3 adopts a modular architecture that separates FL functions from Web3 support services, decoupling the off-chain training and data plane from on-chain settlement while preserving verifiable incentive execution. The framework supports pluggable aggregation and contribution evaluation methods and provides a browser-native DApp interface to lower the participation barrier. We evaluate FWeb3 in real-world settings and show that it supports end-to-end incentive-aware FL with transaction and data-transfer overheads of only 21.3% and 3.4% in WAN; FWeb3 also deploys from zero configuration in under 3 minutes and enables user onboarding in under 1 minute.
Tuan Nguyen Kim, Ha Nguyen Hoang, Son Doan Trung, Lam Nguyen
Cloud computing has become a vital platform for large-scale data analytics, yet it poses significant privacy challenges when handling sensitive information, especially in healthcare and financial domains.Homomorphic Encryption (HE) enables computation on encrypted data, providing strong privacy guarantees, but traditional HE frameworks lack efficient query representation, do not protect query patterns, and cannot prove correctness of cloud-side computations.This paper proposes HE-Cloud, an integrated privacy-preserving framework that combines DSL-driven query compilation, HE, Zero-Knowledge Proofs (ZKP), and Oblivious RAM (ORAM).Our framework allows clients to express high-level analytical queries, securely executes them on encrypted data, protects query access patterns via ORAM, and returns verifiable results through ZKP.A proof-of-concept implementation using the Pima Diabetes dataset demonstrates feasibility: Average glucose computations can be performed entirely on encrypted data with sub-second latency for homomorphic operations and minimal accuracy loss (approximately 0.001).Scalable secure analytics, extendable to larger datasets and machine learning tasks.
Secure and bandwidth-conscious transmission of model updates is a central bottleneck in distributed machine learning. Existing secure aggregation and homomorphic encryption pipelines either reveal more than the task requires or incur prohibitive computation and communication costs. We introduce a verifiable functional encryption (VFE) framework that releases only the intended linear functions of client gradients while providing end-to-end integrity and privacy guarantees under standard lattice assumptions. Our instantiation, FlowAgg-FE, combines two novel components. First, KS-IPFE, a key-splittable inner-product FE scheme, supports per-round weighted aggregation, vector packing, and on-the-fly function changes without client re-encryption; function keys are distributed across two non-colluding helpers, eliminating a single point of trust and enabling lightweight, homomorphically verifiable tags on decrypted outputs. Second, PaS-Stream is a rate-adaptive encryption-and-compression pipeline that couples sketch-based gradient compression with batched FE ciphertext streaming, ensuring unbiased aggregation in the presence of stragglers and dropouts. We further bind client-side clipping to zero-knowledge range proofs and offer an optional differentially private release layer that composes with FE to yield (ε,δ)-privacy. A prototype based on LWE demonstrates practicality across cross-device and cross-silo training: client uplink is reduced by 1.9–3.4× and server CPU time by 1.6× versus state-of-practice encrypted secure aggregation, with accuracy within 0.3% of plaintext baselines and correctness preserved under up to 30% client dropout. These results show that verifiable FE can make secure, communication-efficient gradient transmission viable, as appropriate for theme of security and privacy in distributed machine learning of the Special Issue.
The convergence of social networking and electronic commerce has given rise to the social e-commerce paradigm, where content creators serve as the primary drivers of consumer engagement and purchase decisions. However, this ecosystem faces a critical tension between the need for high-precision ad targeting to sustain monetization and the increasingly stringent requirements for user privacy preservation. Traditional centralized recommendation systems require the aggregation of massive user behavioral datasets, creating significant risks of data leakage and violating emerging regulatory frameworks. To address this challenge, we propose a novel framework titled Fed-ZKC (Federated Zero-Knowledge Creator). This architecture synergizes Federated Learning (FL) with Zero-Knowledge Proofs (ZKP) to enable privacy-preserving ad targeting while ensuring verifiable monetization attribution for creators. In our system, user preference models are trained locally on edge devices to prevent raw data transmission, while a cryptographic verification layer ensures that ad interactions are genuine without revealing user identities to the platform or the creators. Extensive experiments conducted on large-scale real-world datasets demonstrate that Fed-ZKC achieves recommendation accuracy comparable to centralized baselines while reducing privacy leakage risks by orders of magnitude. Furthermore, the implementation of succinct non-interactive arguments of knowledge (zk-SNARKs) introduces minimal computational overhead, making the protocol feasible for deployment on modern mobile processors.
Exponentially growing data generated by networked devices in Industry 4.0 environments requires industrial analytics that are secure, scalable, and decentralized. This article proposes TADDA-4i, a new multi-layered architecture based on IOTA's Tangle-Directed Acyclic Graph (DAG)-based Distributed Ledger Technology (DLT)-combined with federated learning and edge computing to provide real-time, secure, reliable, and self-sovereign industrial analytics. The architecture minimizes centralized bottlenecks via feeless, asynchronous data validation and tamper-evident model update verification using the Tangle ledger. Adaptive Tip-Aware Data Prioritization (ATDP) and Tangle-Validated Federated Aggregation (TVFA) are two new algorithms proposed for improving responsiveness and securing federated learning integrity. Experimental evaluation in emulated industrial edge environments showed that transactions take 30 percent less time, almost all of the misbehaving updates are detected, the model is about 10 percent more accurate, and output is not reduced even if the number of devices reaches 50. These findings make TADDA-4i an executable solution for the future generations of decentralized industrial intelligence.
Abstract Can a dealer share a secret without knowing the shareholders? We provide a positive answer to this question by introducing the concept of an attribute-based secret sharing (AB-SS) scheme.With AB-SS, a dealer can distribute a secret based on attributes rather than specific individuals or shareholders. Only authorized users whose attributes satisfy a given access structure can recover the secret. Furthermore, we introduce the concept of attribute-based publicly verifiable secret sharing (AB-PVSS). An AB-PVSS scheme allows external users to verify the correctness of all broadcast messages from the dealer and shareholders, similar to a traditional PVSS scheme. Additionally, AB-SS (or AB-PVSS) distinguishes itself from traditional SS (or PVSS) by enabling a dealer to generate shares according to an arbitrary monotone access structure.To build an AB-PVSS scheme, we first implement a decentralized ciphertext-policy attribute-based encryption (CP-ABE) scheme, though not a fully-fledged one.We then incorporate non-interactive zero-knowledge (NIZK) proofs to enable public verification of the CP-ABE ciphertext. Based on the CP-ABE and NIZK proofs, we construct an AB-PVSS primitive.Finally, we conduct security analysis and comprehensive experiments on the proposed CP-ABE and AB-PVSS schemes. The results demonstrate that both schemes exhibit plausible performance compared to related works.
Joshua Edward Mamza, Idris Ismaila, Joseph A. Ojeniyi, Shafi’i Abdulhamid · 6 authors
The Common Vulnerability Scoring System (CVSS) depends on reliable vulnerability data from expert, but the current process of vulnerability score generation and transmission remain exposed to data manipulation and interception. Existing research work used supervised machine learning to automate CVSS scoring with up to 90% accuracy, but their plaintext-based approach lacked cryptographic protections, leaving it vulnerable to Man-in-the-Middle (MitM) attacks. Another research work introduced a homomorphic encryption-based framework that preserves data confidentiality during computation and offers moderate performance gains. However, their dependance on a single trusted aggregator, static key management, and absence of dynamic integrity threshold mechanisms left the system exposed if the aggregator’s key or channel were compromised. An architectural framework for an Enhanced Multi-Party Fully Homomorphic Encryption Scheme (EMHES) was designed to combat Man-in-the-Middle (MitM) attacks targeting Vulnerability Score manipulation. By employing Homomorphic Encryption, the framework enables computations on encrypted vulnerability scores, ensuring confidentiality throughout their lifecycle. Key enhancements include integrating digital signatures to authenticate classified scores before encrypted transmission to cloud environments and verify the integrity of decrypted results post-processing. Digital signatures and regulatory oversight significantly strengthen security properties like non-repudiation, integrity, and confidentiality for cloud-based data computations. The EMHES architecture features a secure transmission channel with multiple security layers within the cloud service provider infrastructure. Additional security mechanisms include secure key management protocols, zero-knowledge proofs for integrity verification, and a resilient secure aggregation protocol designed to counter MitM attacks. From a computational analysis, baseline algorithms exhibit constant time complexity O(1), while the EMHES architecture operates with linear time complexity O(n). The result shows that EMHES provides superior security, integrity and performance on large datasets.
Arka Pal, Louai Zahran, William Gvozdjak, Akilesh Potti · 5 authors
As large language models (LLMs) continue to grow in size, fewer users are able to host and run models locally. This has led to increased use of third-party hosting services. However, in this setting, there is a lack of guarantees on the computation performed by the inference provider. For example, a dishonest provider may replace an expensive large model with a cheaper-to-run weaker model and return the results from the weaker model to the user. Existing tools to verify inference typically rely on methods from cryptography such as zero-knowledge proofs (ZKPs), but these add significant computational overhead, and remain infeasible for use for large models. In this work, we develop a new insight -- that given a method for performing private LLM inference, one can obtain forms of verified inference at marginal extra cost. Specifically, we propose two new protocols which leverage privacy-preserving LLM inference in order to provide guarantees over the inference that was carried out. Our approaches are cheap, requiring the addition of a few extra tokens of computation, and have little to no downstream impact. As the fastest privacy-preserving inference methods are typically faster than ZK methods, the proposed protocols also improve verification runtime. Our work provides novel insights into the connections between privacy and verifiability in LLM inference.
Atefeh Nekouie, Majid Vafaei Jahan, Mohammad Hossein Moattar, Reza Sheibani
Access control and data privacy are two of the main necessities in managing electronic health records (EHRs) across distributed domain. There are privacy gaps that expose EHRs to risks like unauthorized access by unaffiliated medical personnel. Traditional attribute-based encryption (ABE) allows encryption based on user attributes but is unable to incorporate data-specific attributes, such as the type of medical information included in the record or the potential physician. This paper introduces a novel approach that integrates ABE with large language models (LLMs) and blockchain technology to enhance security and contextual access control in EHR systems. Specifically, a domain-specific LLM, such as ClinicalBERT, is leveraged to automatically extract semantic data attributes from unstructured medical records, enabling a more granular and context-aware encryption process. By embedding both user and data attributes into the ABE framework, access policies are dynamically refined, ensuring that only authorized users can view specific types of medical information. Furthermore, blockchain's immutable ledger enhances trust, streamlines attribute revocation, and fortifies the system against unauthorized modifications and security threats. The proposed framework significantly strengthens EHR privacy by integrating machine learning-driven attribute extraction with cryptographic access control, outperforming existing schemes in both security and flexibility. Evaluations validate the effectiveness of the proposed framework in preventing unauthorized access while maintaining efficient and transparent data management.
This paper presents a framework that integrates blockchain-enabled Federated Learning (FL) with consensus mechanisms to mitigate poisoning attacks in healthcare environments. The framework incorporates blockchain consensus mechanisms, with Proof-of-Work (PoW) used as a baseline and Proof-of-Stake (PoS) adopted as the proposed approach; both are evaluated independently within the same Secure Multiparty Computation (SMPC)-enabled federated learning architecture for privacy preservation. The proposed system is evaluated on the OCTMNIST and TissueMNIST datasets under both centralized and federated settings, including poisoning scenarios with 10% and 50% malicious clients. Results show that consensus-aware aggregation reduces the influence of unreliable client updates and improves the robustness of the global model under poisoning conditions. In addition, the framework prioritizes trustworthy client contributions during aggregation, supporting reliable model sharing in collaborative healthcare learning environments. Unlike prior blockchain-based federated learning defenses that introduce heavy cryptographic overhead, the proposed PoS-based aggregation explicitly balances robustness and computational efficiency, enabling practical deployment under high poisoning ratios.
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 validation—fake 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 scoring—which could unlock over $100B in overcollateralized capital—to public-good AI for rare diseases, minority languages, and environmental monitoring.
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 (28–32 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.