Search Results for author: Shuchi Wu

Found 2 papers, 0 papers with code

EmInspector: Combating Backdoor Attacks in Federated Self-Supervised Learning Through Embedding Inspection

no code implementations21 May 2024 Yuwen Qian, Shuchi Wu, Kang Wei, Ming Ding, Di Xiao, Tao Xiang, Chuan Ma, Song Guo

To tackle this issue, we dive into the fundamental mechanism of backdoor attacks on FSSL, proposing the Embedding Inspector (EmInspector) that detects malicious clients by inspecting the embedding space of local models.

Refine, Discriminate and Align: Stealing Encoders via Sample-Wise Prototypes and Multi-Relational Extraction

no code implementations1 Dec 2023 Shuchi Wu, Chuan Ma, Kang Wei, Xiaogang Xu, Ming Ding, Yuwen Qian, Tao Xiang

This paper introduces RDA, a pioneering approach designed to address two primary deficiencies prevalent in previous endeavors aiming at stealing pre-trained encoders: (1) suboptimal performances attributed to biased optimization objectives, and (2) elevated query costs stemming from the end-to-end paradigm that necessitates querying the target encoder every epoch.

Cannot find the paper you are looking for? You can Submit a new open access paper.