paper-with-me

홈 › Papers

REMISVFU: Vertical Federated Unlearning via Representation Misdirection for Intermediate Output Feature

2025-12-11 · Wenhan Wu, Zhili He, Huanghuang Liang, Yili Gong, Jiawei Jiang, Chuang Hu, Dazhao Cheng arxiv

Data-protection regulations such as the GDPR grant every participant in a federated system a right to be forgotten. Federated unlearning has therefore emerged as a research frontier, aiming to remove a specific party's contribution from the learned model while preserving the utility of the remaining parties. However, most unlearning techniques focus on Horizontal Federated Learning (HFL), where data are partitioned by samples. In contrast, Vertical Federated Learning (VFL) allows organizations that possess complementary feature spaces to train a joint model without sharing raw data. The resulting feature-partitioned architecture renders HFL-oriented unlearning methods ineffective. In this paper, we propose REMISVFU, a plug-and-play representation misdirection framework that enables fast, client-level unlearning in splitVFL systems. When a deletion request arrives, the forgetting party collapses its encoder output to a randomly sampled anchor on the unit sphere, severing the statistical link between its features and the global model. To maintain utility for the remaining parties, the server jointly optimizes a retention loss and a forgetting loss, aligning their gradients via orthogonal projection to eliminate destructive interference. Evaluations on public benchmarks show that REMISVFU suppresses back-door attack success to the natural class-prior level and sacrifices only about 2.5% points of clean accuracy, outperforming state-of-the-art baselines.

📄 PDF Abstract BibTeX arXiv:2512.10348

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

Feature-Selective Representation Misdirection for Machine Unlearning

2025-12-18 · Taozhao Chen, Linghan Huang, Kim-Kwang Raymond Choo, Huaming Chen arxiv

As large language models (LLMs) are increasingly adopted in safety-critical and regulated sectors, the retention of sensitive or prohibited knowledge introduces escalating risks, ranging from privacy leakage to regulator…

Do Vision Models Truly Forget? New Findings from Representation-Level Certification of Visual Unlearning in Vertical Federated Learning

2026-05-19 · Zhenyu Yu, Yangchen Zeng, Chunlei Meng, Guangzhen Yao 외 arxiv

Machine unlearning in Vertical Federated Learning (VFL) has attracted growing interest, yet existing methods certify forgetting solely using output-level metrics. We challenge these works by introducing Mirage, a represe…

Federated Learning

A few-shot Label Unlearning in Vertical Federated Learning

2024-10-14 · Hanlin Gu, Hong Xi Tae, Chee Seng Chan, Lixin Fan

This paper addresses the critical challenge of unlearning in Vertical Federated Learning (VFL), an area that has received limited attention compared to horizontal federated learning. We introduce the first approach speci…

Computational EfficiencyFederated LearningVertical Federated Learning

Forgetting Any Data at Any Time: A Theoretically Certified Unlearning Framework for Vertical Federated Learning

2025-02-24 · Linian Wang, Leye Wang

Privacy concerns in machine learning are heightened by regulations such as the GDPR, which enforces the "right to be forgotten" (RTBF), driving the emergence of machine unlearning as a critical research field. Vertical F…

Federated LearningMachine UnlearningVertical Federated Learning

Certifying the Right to Be Forgotten: Primal-Dual Optimization for Sample and Label Unlearning in Vertical Federated Learning

2025-12-29 · Yu Jiang, Xindi Tong, Ziyao Liu, Xiaoxi Zhang 외 arxiv

Federated unlearning has become an attractive approach to address privacy concerns in collaborative machine learning, for situations when sensitive data is remembered by AI models during the machine learning process. It …

Federated Learning