{"id":186,"date":"2026-03-28T06:12:13","date_gmt":"2026-03-28T06:12:13","guid":{"rendered":"https:\/\/wp.lancs.ac.uk\/colab\/?p=186"},"modified":"2026-03-28T14:46:02","modified_gmt":"2026-03-28T14:46:02","slug":"186","status":"publish","type":"post","link":"https:\/\/wp.lancs.ac.uk\/colab\/2026\/03\/28\/186\/","title":{"rendered":"Synthetic Data-Driven Conformity Scoring Framework for Robust Federated Learning"},"content":{"rendered":"<p>Our work, &#8220;SD-CSFL: A Synthetic Data-Driven Conformity Scoring Framework for Robust Federated Learning&#8221; was presented at WACV 2026. The work introduces a novel technique for robust federated learning, based on using synthetic data to defend against adversaries in a privacy-preserving way. Results show improved performance against both gradient manipulation and backdoors. Our paper is <a href=\"https:\/\/openaccess.thecvf.com\/content\/WACV2026\/papers\/Alharbi_SD-CSFL_A_Synthetic_Data-Driven_Conformity_Scoring_Framework_for_Robust_Federated_WACV_2026_paper.pdf\">freely available<\/a>, and our code is available on <a href=\"https:\/\/github.com\/EbtisaamCS\/SD-CSFL\">GitHub<\/a>.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" src=\"http:\/\/wp.lancs.ac.uk\/colab\/files\/2026\/03\/FMW-1024x381.png\" alt=\"Overview of our framework.\" width=\"676\" height=\"252\" class=\"aligncenter size-large wp-image-187\" srcset=\"https:\/\/wp.lancs.ac.uk\/colab\/files\/2026\/03\/FMW-1024x381.png 1024w, https:\/\/wp.lancs.ac.uk\/colab\/files\/2026\/03\/FMW-300x112.png 300w, https:\/\/wp.lancs.ac.uk\/colab\/files\/2026\/03\/FMW-768x286.png 768w, https:\/\/wp.lancs.ac.uk\/colab\/files\/2026\/03\/FMW-1536x571.png 1536w, https:\/\/wp.lancs.ac.uk\/colab\/files\/2026\/03\/FMW-676x251.png 676w, https:\/\/wp.lancs.ac.uk\/colab\/files\/2026\/03\/FMW.png 1930w\" sizes=\"auto, (max-width: 676px) 100vw, 676px\" \/><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Our work, &#8220;SD-CSFL: A Synthetic Data-Driven Conformity Scoring Framework for Robust Federated Learning&#8221; was presented at WACV 2026. The work introduces a novel technique for robust federated learning, based on using synthetic data to defend against adversaries in a privacy-preserving way. Results show improved performance against both gradient manipulation and backdoors. Our paper is freely [&hellip;]<\/p>\n","protected":false},"author":1432,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[3],"tags":[],"class_list":["post-186","post","type-post","status-publish","format-standard","hentry","category-news"],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/wp.lancs.ac.uk\/colab\/wp-json\/wp\/v2\/posts\/186","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/wp.lancs.ac.uk\/colab\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/wp.lancs.ac.uk\/colab\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/wp.lancs.ac.uk\/colab\/wp-json\/wp\/v2\/users\/1432"}],"replies":[{"embeddable":true,"href":"https:\/\/wp.lancs.ac.uk\/colab\/wp-json\/wp\/v2\/comments?post=186"}],"version-history":[{"count":2,"href":"https:\/\/wp.lancs.ac.uk\/colab\/wp-json\/wp\/v2\/posts\/186\/revisions"}],"predecessor-version":[{"id":189,"href":"https:\/\/wp.lancs.ac.uk\/colab\/wp-json\/wp\/v2\/posts\/186\/revisions\/189"}],"wp:attachment":[{"href":"https:\/\/wp.lancs.ac.uk\/colab\/wp-json\/wp\/v2\/media?parent=186"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/wp.lancs.ac.uk\/colab\/wp-json\/wp\/v2\/categories?post=186"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/wp.lancs.ac.uk\/colab\/wp-json\/wp\/v2\/tags?post=186"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}