Fed-FBD: Federated Functional Block Diversification for Isolation, Privacy, and Surgical Unlearning

Computer Science > Machine Learning [Submitted on 10 Jun 2026] Fed-FBD: Federated Functional Block Diversification for Isolation, Privacy, and Surgical Unlearning Weijie Chen, Alan B. McMillan Federated learning (FL) enables collaborative model training without sharing raw patient data, but standard approaches such as FedAvg treat each client as a black box and provide no mechanism for isolating an adversarial contributor, auditing per-client influence, or honoring a departed participant's right to be forgotten. We present Fed-FBD (Federated Functional Block Diversification), a modular federated architecture that decomposes a ResNet backbone into six functional blocks (the stem, four residual groups, and the classification head) and maintains a warehouse of N color variants, each assembled from independently tracked and contributor-stamped blocks. Fed-FBD provides three capabilities absent in FedAvg: (i) architecturally guaranteed block-level isolation, so that an adversarial or mislabelled client cannot contaminate the clean colous; (ii) privacy-by-design, where membership inference advantage is already indistinguishable from chance before any privacy mechanism is applied; and (iii) surgical machine unlearning of a departed participant's contribution at sub-second cost and without retraining. Experiments on six MedMNIST-2D datasets, PathMNIST at 224x224, and CIFAR-10 show that Fed-FBD trades a modest 0.3%-3.1% IID accuracy gap on the adequately sized datasets for these guarantees, remains within 0.8%-4.0% of FedAvg at Dirichlet alpha=1.0 on three of four datasets, and confines all six adversarial attacks we study to the poisoned client's own blocks with at most +/-0.01 AUC drift on the clean colors. Comments: 12 pages, 3 figures, 8 tables. Code: this https URL Subjects: Machine Learning (cs.LG); Cryptography and Security (cs.CR); Image and Video Processing (eess.IV) MSC classes: 68T07, 68T05 ACM classes: I.2.6; I.4.9; K.6.5 Cite as: arXiv:2606.12679 [cs.LG]   (or arXiv:2606.12679v1 [cs.LG] for this version)   https://doi.org/10.48550/arXiv.2606.12679 Focus to learn more Submission history From: Weijie Chen [view email] [v1] Wed, 10 Jun 2026 21:06:10 UTC (88 KB) Access Paper: HTML (experimental) view license Current browse context: cs.LG < prev   |   next > new | recent | 2026-06 Change to browse by: cs cs.CR eess eess.IV References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)