Foundation models are commonly deployed as frozen feature extractors with a small trainable head to adapt to private, user-generated data in federated settings. The ``right to be forgotten'' requires removing the influence of specific samples or users from the trained model on demand. Existing federated unlearning methods target general deep models and rely on approximate reconstruction or selective retraining, making exactness costly or elusive. We study this problem in a practically relevant but under-explored regime: a frozen foundation model with a ridge-regression head. The exact optimum depends on the data only through two additive sufficient statistics, which we turn into a communication protocol supporting an arbitrary stream of add and delete requests via fixed-size messages. The server maintains a head that is, in exact arithmetic, pointwise identical to centralized retraining after every request. We provide deterministic retrain-equivalence guarantees, order and partition invariance, two server-side variants, and a Bayesian certificate of zero KL divergence. Experiments on four benchmarks confirm the guarantees: both variants match centralized ridge retraining to within $10^{-9}$ relative Frobenius error and complete each request at orders-of-magnitude lower cost than federated retraining baselines.
Don't Break the Boundary: Continual Unlearning for OOD Detection Based on Free Energy Repulsion
School of Computer and Electronic Information, Nanjing Normal University（计算机与电子信息学院，南京师范大学）；School of Artificial Intelligence and Information Technology, Nanjing University of Chinese Medicine（人工智能与信息科技学院，南京中医药大学）
Orthogonal Subspace Projection for Continual Machine Unlearning via SVD-Based LoRA
Institute for Digital Technologies, Loughborough University, UK（伦敦大学数字技术研究所，英国）；School of Artificial Intelligent Medicine, Guilin Medical University（桂林医学院人工智能医学院）
ErrorEraser: Unlearning Data Bias for Improved Continual Learning
School of Computing and Artificial Intelligence, Southwestern University of Finance and Economics（西南财经大学计算机与人工智能学院）；School of Computing and Artificial Intelligence, Southwest Jiaotong University（西南交通大学计算机与人工智能学院）
FRAMU: Attention-based Machine Unlearning using Federated Reinforcement Learning
University of Southern Queensland（南昆士兰大学）；Wuhan University of Technology（武汉理工大学）；Lingnan University（岭南大学）；University of Electronic Science and Technology of China（电子科技大学）；Hong Kong Polytechnic University（香港理工大学）
Bringing Multi-Modal Multi-Task Federated Foundation Models to Education Domain: Prospects and Challenges
University at Buffalo –SUNY, Department of Electrical Engineering（布法罗大学–纽约州立大学，电气工程系）；Adobe Research（Adobe研究）；University of California – San Diego, Department of Electrical and Computer Engineering（加州大学圣地亚哥分校，电气与计算机工程系）；NC State University, Department of Computer Science（北卡罗来纳州立大学，计算机科学系）
Ten Challenging Problems in Federated Foundation Models
WeBank（微众银行）；Universiti Malaya（马来亚大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Duke Kunshan University（昆山杜克大学）；KTH Royal Institute of Technology（瑞典皇家理工学院）；Beihang University（北京航空航天大学）；Shanghai Jiao Tong University（上海交通大学）；Xi’an Jiaotong University（西安交通大学）；Southwestern University of Finance and Economic（西南财经大学）
