paper-with-me

홈 › Papers

VFLIP: A Backdoor Defense for Vertical Federated Learning via Identification and Purification

2024-08-28 · Yungi Cho, Woorim Han, Miseon Yu, Younghan Lee, Ho Bae, Yunheung Paek

Vertical Federated Learning (VFL) focuses on handling vertically partitioned data over FL participants. Recent studies have discovered a significant vulnerability in VFL to backdoor attacks which specifically target the distinct characteristics of VFL. Therefore, these attacks may neutralize existing defense mechanisms designed primarily for Horizontal Federated Learning (HFL) and deep neural networks. In this paper, we present the first backdoor defense, called VFLIP, specialized for VFL. VFLIP employs the identification and purification techniques that operate at the inference stage, consequently improving the robustness against backdoor attacks to a great extent. VFLIP first identifies backdoor-triggered embeddings by adopting a participant-wise anomaly detection approach. Subsequently, VFLIP conducts purification which removes the embeddings identified as malicious and reconstructs all the embeddings based on the remaining embeddings. We conduct extensive experiments on CIFAR10, CINIC10, Imagenette, NUS-WIDE, and BankMarketing to demonstrate that VFLIP can effectively mitigate backdoor attacks in VFL. https://github.com/blingcho/VFLIP-esorics24

📄 PDF Abstract BibTeX arXiv:2408.15591

Code (1)

blingcho/vflip-esorics24 공식 구현 pytorch

Tasks

Anomaly Detectionbackdoor defenseFederated LearningVertical Federated Learning

Similar Papers 제목 키워드 기반

Backdoor Attack on Vertical Federated Graph Neural Network Learning

2024-10-15 · Jirui Yang, Peng Chen, Zhihui Lu, Ruijun Deng 외

Federated Graph Neural Network (FedGNN) integrate federated learning (FL) with graph neural networks (GNNs) to enable privacy-preserving training on distributed graph data. Vertical Federated Graph Neural Network (VFGNN)…

Backdoor AttackFederated LearningGraph Neural NetworkPrivacy Preserving

Mutual Information Regularization for Vertical Federated Learning

2023-01-01 · Tianyuan Zou, Yang Liu, Ya-Qin Zhang

Vertical Federated Learning (VFL) is widely utilized in real-world applications to enable collaborative learning while protecting data privacy and safety. However, previous works show that parties without labels (passive…

Federated LearningVertical Federated Learning

Is the Trigger Essential? A Feature-Based Triggerless Backdoor Attack in Vertical Federated Learning

2026-02-24 · Yige Liu, Yiwei Lou, Che Wang, Yongzhi Cao 외 arxiv

As a distributed collaborative machine learning paradigm, vertical federated learning (VFL) allows multiple passive parties with distinct features and one active party with labels to collaboratively train a model. Althou…

Federated Learning

GANcrop: A Contrastive Defense Against Backdoor Attacks in Federated Learning

2024-05-31 · Xiaoyun Gan, Shanyu Gan, Taizhi Su, Peng Liu

With heightened awareness of data privacy protection, Federated Learning (FL) has attracted widespread attention as a privacy-preserving distributed machine learning method. However, the distributed nature of federated l…

Contrastive LearningFederated LearningPrivacy Preserving

Understanding Backdoor Vulnerabilities in Vertical Federated Learning: The Gap Between Research and Practice

2026-08-13 · Ziqi Zhao, Jialin Lu, Junjie Shan, Junyuan Zhang 외 arxiv

Vertical Federated Learning (VFL) enables organizations holding complementary features of shared entities to collaborate and train models. In this setting, the initiator can withhold information about the learning task, …

Federated Learning