paper-with-me

홈 › Papers

Query-Efficient Adversarial Attack Against Vertical Federated Graph Learning

2024-11-05 · Jinyin Chen, Wenbo Mu, Luxin Zhang, Guohan Huang, Haibin Zheng, Yao Cheng

Graph neural network (GNN) has captured wide attention due to its capability of graph representation learning for graph-structured data. However, the distributed data silos limit the performance of GNN. Vertical federated learning (VFL), an emerging technique to process distributed data, successfully makes GNN possible to handle the distributed graph-structured data. Despite the prosperous development of vertical federated graph learning (VFGL), the robustness of VFGL against the adversarial attack has not been explored yet. Although numerous adversarial attacks against centralized GNNs are proposed, their attack performance is challenged in the VFGL scenario. To the best of our knowledge, this is the first work to explore the adversarial attack against VFGL. A query-efficient hybrid adversarial attack framework is proposed to significantly improve the centralized adversarial attacks against VFGL, denoted as NA2, short for Neuron-based Adversarial Attack. Specifically, a malicious client manipulates its local training data to improve its contribution in a stealthy fashion. Then a shadow model is established based on the manipulated data to simulate the behavior of the server model in VFGL. As a result, the shadow model can improve the attack success rate of various centralized attacks with a few queries. Extensive experiments on five real-world benchmarks demonstrate that NA2 improves the performance of the centralized adversarial attacks against VFGL, achieving state-of-the-art performance even under potential adaptive defense where the defender knows the attack method. Additionally, we provide interpretable experiments of the effectiveness of NA2 via sensitive neurons identification and visualization of t-SNE.

📄 PDF Abstract BibTeX arXiv:2411.02809

Code (1)

hgh0545/NA2 공식 구현 pytorch

Tasks

Adversarial AttackFederated LearningGraph LearningGraph Neural NetworkGraph Representation LearningRepresentation LearningVertical Federated Learning

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Defending against Reconstruction Attack in Vertical Federated Learning

2021-07-21 · Jiankai Sun, Yuanshun Yao, Weihao Gao, Junyuan Xie 외

Recently researchers have studied input leakage problems in Federated Learning (FL) where a malicious party can reconstruct sensitive training inputs provided by users from shared gradient. It raises concerns about FL si…

Federated LearningPrivacy PreservingReconstruction AttackVertical Federated Learning

PRIVEE: Privacy-Preserving Vertical Federated Learning Against Feature Inference Attacks

2025-12-14 · Sindhuja Madabushi, Ahmad Faraz Khan, Haider Ali, Ananthram Swami 외 arxiv

Vertical Federated Learning (VFL) enables collaborative model training across organizations that share common user samples but hold disjoint feature spaces. Despite its potential, VFL is susceptible to feature inference …

Federated Learning

Analyzing the Robustness of Decentralized Horizontal and Vertical Federated Learning Architectures in a Non-IID Scenario

2022-10-20 · Pedro Miguel Sánchez Sánchez, Alberto Huertas Celdrán, Enrique Tomás Martínez Beltrán, Daniel Demeter 외

Federated learning (FL) allows participants to collaboratively train machine and deep learning models while protecting data privacy. However, the FL paradigm still presents drawbacks affecting its trustworthiness since m…

Data PoisoningFederated LearningPrivacy PreservingVertical Federated Learning

RVFR: Robust Vertical Federated Learning via Feature Subspace Recovery

2021-09-29 · Jing Liu, Chulin Xie, Krishnaram Kenthapadi, Oluwasanmi O Koyejo 외

Vertical Federated Learning (VFL) is a distributed learning paradigm that allows multiple agents to jointly train a global model when each agent holds a different subset of features for the same sample(s). VFL is known t…

Federated LearningVertical Federated Learning

KDk: A Defense Mechanism Against Label Inference Attacks in Vertical Federated Learning

2024-04-18 · Marco Arazzi, Serena Nicolazzo, Antonino Nocera

Vertical Federated Learning (VFL) is a category of Federated Learning in which models are trained collaboratively among parties with vertically partitioned data. Typically, in a VFL scenario, the labels of the samples ar…

Federated LearningKnowledge DistillationVertical Federated Learning