Search Results for author:
Found 3 papers, 0 papers with code
LabObf: A Label Protection Scheme for Vertical Federated Learning Through Label Obfuscation
In this paper, we first propose an embedding extension attack that manually modifies embeddings to undermine existing defense strategies, which rely on constraining the correlation between the embeddings uploaded by participants and the labels.
A Split-and-Privatize Framework for Large Language Model Fine-Tuning
Fine-tuning is a prominent technique to adapt a pre-trained language model to downstream scenarios.
Secure Split Learning against Property Inference, Data Reconstruction, and Feature Space Hijacking Attacks
Split learning of deep neural networks (SplitNN) has provided a promising solution to learning jointly for the mutual interest of a guest and a host, which may come from different backgrounds, holding features partitioned vertically.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
