2 papers
cs.CR2025
How Breakable Is Privacy: Probing and Resisting Model Inversion Attacks in Collaborative Inference
Rongke Liu, Youwen Zhu, Dong Wang +3
Collaborative inference (CI) improves computational efficiency for edge devices by transmitting intermediate features to cloud models. However, this process inevitably exposes feat…
cs.LG2024
URVFL: Undetectable Data Reconstruction Attack on Vertical Federated Learning
Duanyi Yao, Songze Li, Xueluan Gong +2
Launching effective malicious attacks in VFL presents unique challenges: 1) Firstly, given the distributed nature of clients' data features and models, each client rigorously guard…