← Search

Ruizhi Zhao

2 accepted papers

2024

Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks

AAAI 2024technical

Collaborative learning (CL) is a distributed learning framework that aims to protect user privacy by allowing users to jointly train a model by sharing their gradient updates only. However, gradient inversion attacks (GIAs), which recover users' training data from shared gradients, impose severe pri…

Cited by 2SourcePDFScholar
2023

Downstream-agnostic Adversarial Examples

ICCV 2023poster

Self-supervised learning usually uses a large amount of unlabeled data to pre-train an encoder which can be used as a general-purpose feature extractor, such that downstream users only need to perform fine-tuning operations to enjoy the benefit of "big model". Despite this promising prospect, the se…

Cited by 30PDFcodeScholar