{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T16:03:03Z","timestamp":1775836983801,"version":"3.50.1"},"reference-count":27,"publisher":"Emerald","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,15]]},"abstract":"<jats:sec>\n                  <jats:title>Purpose<\/jats:title>\n                  <jats:p>The growing concern over privacy leakage has led to reduced user participation in data sharing, prompting the exploration of novel techniques such as federated learning (FL). Meanwhile, existing FL solutions often overlook the validation of the training process, leaving room for malicious trainers to introduce false or toxic local models, detrimental to the global model\u2019s utility. This study aims to propose a zero-knowledge proof-based verifiable federated learning (ZKP-FL) framework on the blockchain.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Design\/methodology\/approach<\/jats:title>\n                  <jats:p>ZKP-FL leverages zero-knowledge proofs to verify the extensive local training process without threatening the local privacy. To reduce the memory and runtime overhead, the authors divide the training algorithm to be proven into smaller pieces and generating proofs for each segment. The authors leverage sigma-protocol to ensure the consistency and reliability of these proofs. Moreover, they design a secure model aggregation protocol that matches the local proofs, safeguarding the data privacy of individual local models throughout the process. Furthermore, this aggregation protocol can also guarantee the correctness of the aggregation.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Findings<\/jats:title>\n                  <jats:p>To establish the effectiveness and security of ZKP-FL, the authors conduct a formal security analysis in terms of completeness, soundness and zero-knowledge properties. Experimental evaluations with different algorithms and models within the ZKP-FL framework demonstrate that with parallel execution the additional proof time per round is minimal.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Originality\/value<\/jats:title>\n                  <jats:p>This paper offers a novel perspective on security and privacy of FL, providing valuable insights that extend the current understanding of verifiable FL. The findings contribute to the ZKP-FL, highlighting areas for future research and practical applications.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1108\/ijwis-01-2025-0024","type":"journal-article","created":{"date-parts":[[2025,4,14]],"date-time":"2025-04-14T23:57:31Z","timestamp":1744675051000},"page":"275-297","source":"Crossref","is-referenced-by-count":4,"title":["Integrating zero-knowledge proofs into federated learning: a path to on-chain verifiable and privacy-preserving federated learning frameworks"],"prefix":"10.1108","volume":"21","author":[{"given":"Chunlei","family":"Li","sequence":"first","affiliation":[{"name":"Beijing Institute of Technology School of Cyberspace Science and Technology, , Beijing,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhibo","family":"Xing","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology School of Cyberspace Science and Technology, , Beijing,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiamou","family":"Liu","sequence":"additional","affiliation":[{"name":"The University of Auckland School of Computer Science, , Auckland,","place":["New Zealand"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giovanni","family":"Russello","sequence":"additional","affiliation":[{"name":"The University of Auckland School of Computer Science, , Auckland,","place":["New Zealand"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology School of Cyberspace Science and Technology, , Beijing,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Wu","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology School of Cyberspace Science and Technology, , Beijing,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Li","sequence":"additional","affiliation":[{"name":"Hefei University of Technology School of Computer Science and Information Engineering, , Hefei,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad Rizwan","family":"Asghar","sequence":"additional","affiliation":[{"name":"University of Surrey School of Computer Science, , Guildford,","place":["UK"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"140","published-online":{"date-parts":[[2025,4,16]]},"reference":[{"key":"2025081308470027000_ref001","first-page":"1","article-title":"zkFDL: an efficient and privacy-preserving decentralized federated learning with zero knowledge proof","author":"Ahmadi","year":"2024"},{"key":"2025081308470027000_ref002","article-title":"Flower: a friendly federated learning research framework","author":"Beutel","year":"2020"},{"key":"2025081308470027000_ref003","first-page":"1175","article-title":"Practical secure aggregation for privacy-preserving machine learning","author":"Bonawitz","year":"2017"},{"key":"2025081308470027000_ref004","article-title":"Rofl: attestable robustness for secure federated learning","author":"Burkhalter","year":"2021"},{"key":"2025081308470027000_ref005","doi-asserted-by":"crossref","first-page":"499","DOI":"10.1007\/978-3-642-36594-2_28","article-title":"Multi-client non-interactive verifiable computation","volume-title":"Theory of Cryptography Conference","author":"Choi","year":"2013"},{"key":"2025081308470027000_ref006","first-page":"84","article-title":"On \u03a3-protocols","volume-title":"Lecture Notes","author":"Damg\u00e5rd","year":"2002"},{"key":"2025081308470027000_ref007","unstructured":"Fisher\n           (1936), \u201cUCI machine learning respository: iris data set\u201d, available at: https:\/\/archive.ics.uci.edu\/ml\/datasets\/iris\/ (accessed 31 july 2023)."},{"key":"2025081308470027000_ref008","doi-asserted-by":"crossref","first-page":"626","DOI":"10.1007\/978-3-642-38348-9_37","article-title":"Quadratic span programs and succinct NIZKs without PCPs","volume-title":"Advances in Cryptology\u2013EUROCRYPT 2013: 32nd Annual International Conference on the Theory and Applications of Cryptographic Techniques","author":"Gennaro","year":"2013"},{"key":"2025081308470027000_ref009","first-page":"4675","article-title":"SafetyNets: verifiable execution of deep neural networks on an untrusted cloud","author":"Ghodsi","year":"2017"},{"key":"2025081308470027000_ref010","first-page":"305","article-title":"On the size of pairing-based non-interactive arguments","author":"Groth","year":"2016"},{"key":"2025081308470027000_ref011","article-title":"Secure weighted aggregation for federated learning","author":"Guo","year":"2020"},{"key":"2025081308470027000_ref012","doi-asserted-by":"crossref","first-page":"1736","DOI":"10.1109\/TIFS.2020.3043139","article-title":"Verifl: communication-efficient and fast verifiable aggregation for federated learning","volume":"16","author":"Guo","year":"2020","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"2025081308470027000_ref013","article-title":"Versa: verifiable secure aggregation for cross-device federated learning","volume-title":"IEEE Transactions on Dependable and Secure Computing.","author":"Hahn","year":"2021"},{"key":"2025081308470027000_ref014","unstructured":"Harrison, D. and Rubinfeld, D.L. (1978), \u201cBoston dataset\u201d, available at: www.cs.toronto.edu\/\u223cdelve\/data\/boston\/bostonDetail.html (accessed 31 july 2023)."},{"key":"2025081308470027000_ref015","article-title":"Federify: a verifiable federated learning scheme based on zksnarks and blockchain","volume-title":"IEEE Access.","author":"Keshavarzkalhori","year":"2023"},{"key":"2025081308470027000_ref016","unstructured":"LeCun, Y., Cortes, C. and Burges, C.J. (2010), \u201cMNIST handwritten digit database\u201d, ATT Labs, Vol. 2, available at: http:\/\/yann.lecun.com\/exdb\/mnist"},{"key":"2025081308470027000_ref017","first-page":"2968","article-title":"ZkCNN: zero knowledge proofs for convolutional neural network predictions and accuracy","author":"Liu","year":"2021"},{"key":"2025081308470027000_ref018","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Artificial Intelligence and Statistics","author":"McMahan","year":"2017"},{"key":"2025081308470027000_ref019","doi-asserted-by":"crossref","first-page":"103561","DOI":"10.1016\/j.csi.2021.103561","article-title":"Privacy-preserving byzantine-robust federated learning","volume":"80","author":"Ma","year":"2022","journal-title":"Computer Standards and Interfaces"},{"key":"2025081308470027000_ref020","first-page":"21260","article-title":"Bitcoin: a peer-to-peer electronic cash system","author":"Nakamoto","year":"2008","journal-title":"Decentralized Business Review"},{"key":"2025081308470027000_ref021","doi-asserted-by":"crossref","first-page":"108621","DOI":"10.1016\/j.comnet.2021.108621","article-title":"Fairness, integrity, and privacy in a scalable blockchain-based federated learning system","volume":"202","author":"R\u00fcckel","year":"2022","journal-title":"Computer Networks"},{"key":"2025081308470027000_ref022","doi-asserted-by":"crossref","unstructured":"Szabo, N.\n           (1997), \u201cFormalizing and securing relationships on public networks\u201d, First monday, Technologies, Parity (2023). Home\u2014Substrate, available at: https:\/\/substrate.io\/ (accessed 31 july 2023).","DOI":"10.5210\/fm.v2i9.548"},{"key":"2025081308470027000_ref023","unstructured":"Thibaut, S. and Darko, M. (2023), \u201cZoKrates:a toolbox for zkSNARKs on ethereum\u201d, available at: https:\/\/github.com\/Zokrates\/ZoKrates (accessed 31 july 2023)."},{"key":"2025081308470027000_ref024","doi-asserted-by":"crossref","first-page":"911","DOI":"10.1109\/TIFS.2019.2929409","article-title":"Verifynet: secure and verifiable federated learning","volume":"15","author":"Xu","year":"2019","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"2025081308470027000_ref025","first-page":"2039","article-title":"Zero knowledge proofs for decision tree predictions and accuracy","author":"Zhang","year":"2020"},{"issue":"10","key":"2025081308470027000_ref026","doi-asserted-by":"crossref","first-page":"2524","DOI":"10.1109\/TPDS.2021.3068195","article-title":"Veriml: enabling integrity assurances and fair payments for machine learning as a service","volume":"32","author":"Zhao","year":"2021","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"2025081308470027000_ref027","article-title":"Deep leakage from gradients","volume":"32","author":"Zhu","year":"2019","journal-title":"Advances in Neural Information Processing Systems"}],"container-title":["International Journal of Web Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/IJWIS-01-2025-0024\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/ijwis\/article-pdf\/21\/3\/275\/10063588\/ijwis-01-2025-0024.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/www.emerald.com\/ijwis\/article-pdf\/21\/3\/275\/10063588\/ijwis-01-2025-0024.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T12:47:09Z","timestamp":1755089229000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.emerald.com\/ijwis\/article\/21\/3\/275\/1273626\/Integrating-zero-knowledge-proofs-into-federated"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,16]]},"references-count":27,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,5,15]]}},"URL":"https:\/\/doi.org\/10.1108\/ijwis-01-2025-0024","relation":{},"ISSN":["1744-0084","1744-0092"],"issn-type":[{"value":"1744-0084","type":"print"},{"value":"1744-0092","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,16]]}}}