BlindSage: Label Inference Attacks against Node-level Vertical Federated Graph Neural Networks

Attackers Are Not the Same! Unveiling the Impact of Feature Distribution on Label Inference Attacks

Y Liu, C Wang, Y Lou, Y Cao… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
As a distributed machine learning paradigm, vertical federated learning enables multiple
passive parties with distinct features and an active party with labels to train a model …
相关文章
[PDF] arxiv.org

Subject Data Auditing via Source Inference Attack in Cross-Silo Federated Learning

J Li, M Arazzi, A Nocera, M Conti - arXiv preprint arXiv:2409.19417, 2024 - arxiv.org
Source Inference Attack (SIA) in Federated Learning (FL) aims to identify which client used a
target data point for local model training. It allows the central server to audit clients' data …
相关文章 所有 2 个版本
[PDF] arxiv.org

Let's Focus: Focused Backdoor Attack against Federated Transfer Learning

M Arazzi, S Koffas, A Nocera, S Picek - arXiv preprint arXiv:2404.19420, 2024 - arxiv.org
Federated Transfer Learning (FTL) is the most general variation of Federated Learning.
According to this distributed paradigm, a feature learning pre-step is commonly carried out …
相关文章 所有 2 个版本
[PDF] ijcai.org

[PDF][PDF] Label Leakage in Vertical Federated Learning: A Survey

Y Liu, Y Lou, Y Liu, Y Cao, H Wang - ijcai.org
Vertical federated learning (VFL) is a distributed machine learning paradigm that
collaboratively trains models using passive parties with features and an active party with …
相关文章