[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85108-en":3,"doc-seo-85108-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},85108,687197207057,"Sage","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Secure Decentralized Federated Learning via Gossip and Virtual Voting","Decentralized federated learning exchanges model updates through peer-to-peer gossip without a central server, yet common gossip-based methods struggle with provenance finality and resilience against Byzantine or lazy participants. Ledger-assisted FL improves auditability, but blockchain-style coordination can reintroduce global overhead that undermines DFL locality. The paper introduces gspDAG-FL: consensus is derived from the same gossip history, using Hashgraph-style virtual voting and compact certificates. Safety, conditional liveness, and convergence for certified perturbed gossip are proved, with experiments on MNIST and Penn Treebank showing ledger-like quality, higher throughput, and strong invalid-origin detection.","Secure Decentralized Federated Learning via Gossip and Virtual Voting  \nAmirhossein Taherpour , and Xiaodong Wang , Fellow, IEEE  \narXiv :2607 .0865 1v 1 [ cs .LG] 9 Jul 2026  \nAbstract—Decentralized federated learning (DFL) removes the central server by letting nodes exchange model updates through peer-to-peer gossip, but existing gossip-based methods often lack provenance finality and resilience to Byzantine or lazy participants. Ledger-assisted federated learning (FL) improves auditability, yet blockchains, shards, or settlement committees can reintroduce global coordination costs that conflict with DFL locality. This paper proposes gspDAGFL, a secure DFL framework that derives consensus from the same gossip history used to disseminate models. Nodes exchange model payloads only with neighbors, while full nodes collect event certificates and receiver-endorsed accepted gossip proofs, reconstruct a compact Topology directed acyclic graph (DAG), and run Hashgraph-style virtual voting followed by compact full-node certificates. Finality is over unique modelorigin tuples, not identical local parameter states. To improve resilience, gspDAG-FL combines payload validation, acceptedproof validation, and private semantic audit before aggregation. We formalize the adversarial setting, prove safety and conditional liveness of the control plane, and give a convergence guarantee for certified perturbed gossip under time-varying effective mixing. Experiments on MNIST classification and Penn Treebank language modeling, using fair held-out validation/audit data and networks up to N = 100, show that gspDAG-FL achieves learning quality close to validation-based ledger FL while reducing coordination bottlenecks, improving throughput, and maintaining high invalid-origin detection under mixed Byzantine and lazy participation.  \nIndex Terms—Decentralized federated learning (DFL), gossip, Hashgraph, directed acyclic graph (DAG), Byzantine fault tolerance (BFT), virtual voting, federated learning security, auditability.  \nI. Introduction  \nFederated learning (FL) trains a model across distributed devices or institutions while keeping raw data local and exchanging only model-side information [1]–[3] . In the standard architecture, a central server coordinates local training, aggregation, and model redistribution, often through federated averaging and secure aggregation [4] . This architecture is effective, but it concentrates coordination, trust, and failure modes at the server. It may also amplify privacy risk, since gradients and model updates can leak sensitive information even when raw data are never shared [5] .  \nA natural alternative is decentralized federated learning (DFL), where peers exchange updates directly through a communication graph. Randomized gossip and decentralized stochastic optimization show that repeated neighbor  \nAmirhossein Taherpour and Xiaodong Wang are with the Department of Electrical Engineering, Columbia University, New York, NY, USA (e-mails: [at3532@columbia.edu](at3532@columbia.edu), [xw2008@columbia.edu](xw2008@columbia.edu)).  \naveraging can converge at a rate controlled by topology and mixing quality [6], [7] . Asynchronous push–pull, pushsum, and compressed gossip variants improve wall-clock efficiency or communication cost under heterogeneous links [8]–[10] . Recent systems such as GossipFL, FedDual, and semi-decentralized optimization further show that neighbor-to-neighbor communication can reduce central bottlenecks [11]–[14] . However, most serverless gossipbased methods assume benign participation. They usually do not provide a system-wide record of update provenance, nor do they define which model origins are final and eligible for aggregation when some nodes are Byzantine, lazy, or behaviorally malicious.  \nRobust aggregation addresses part of this problem by limiting the effect of abnormal updates during aggregation. Byzantine-resilient rules and coordinate-wise robust methods improve resilience under bo","cbCaiqlkR3qVy8Xr","https://ap.wps.com/l/cbCaiqlkR3qVy8Xr","pdf",620842,1,14,"English","en",105,"# Introduction\n## Federated learning and centralized coordination\n## Decentralized federated learning and gossip optimization\n## Limitations of gossip-only methods: provenance and finality\n## Robust aggregation and backdoor defenses\n## Ledger-assisted FL and its coordination costs\n## Core gap: gossip-native consensus for DFL","[{\"question\":\"What problem does gspDAG-FL address in gossip-based decentralized federated learning?\",\"answer\":\"It addresses the lack of provenance finality and resilience when nodes are Byzantine, lazy, or behaviorally malicious, ensuring that updates have sufficient provenance and can be agreed eligible for aggregation.\"},{\"question\":\"How does gspDAG-FL achieve consensus and finality without a central server?\",\"answer\":\"Nodes exchange model payloads with neighbors while full nodes collect event certificates and receiver-endorsed accepted gossip proofs to reconstruct a compact DAG, then run Hashgraph-style virtual voting followed by compact full-node certificates.\"},{\"question\":\"What resilience and performance benefits are reported for gspDAG-FL?\",\"answer\":\"The method combines payload validation, accepted-proof validation, and private semantic audit before aggregation, improving invalid-origin detection and maintaining learning quality close to validation-based ledger FL while reducing coordination bottlenecks and increasing throughput.\"}]",1784201142,35,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"secure-decentralized-federated-learning-via-gossip-and-virtual-voting","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/secure-decentralized-federated-learning-via-gossip-and-virtual-voting/85108/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does gspDAG-FL address in gossip-based decentralized federated learning?","Question",{"text":75,"@type":76},"It addresses the lack of provenance finality and resilience when nodes are Byzantine, lazy, or behaviorally malicious, ensuring that updates have sufficient provenance and can be agreed eligible for aggregation.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does gspDAG-FL achieve consensus and finality without a central server?",{"text":80,"@type":76},"Nodes exchange model payloads with neighbors while full nodes collect event certificates and receiver-endorsed accepted gossip proofs to reconstruct a compact DAG, then run Hashgraph-style virtual voting followed by compact full-node certificates.",{"name":82,"@type":73,"acceptedAnswer":83},"What resilience and performance benefits are reported for gspDAG-FL?",{"text":84,"@type":76},"The method combines payload validation, accepted-proof validation, and private semantic audit before aggregation, improving invalid-origin detection and maintaining learning quality close to validation-based ledger FL while reducing coordination bottlenecks and increasing throughput.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]