most citedAre You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark

2 citations · 3 across the 3 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2023★ 1 cited

Towards Attack-tolerant Federated Learning via Critical Parameter Analysis

Sungwon Han, Sungwon Park, Fangzhao Wu +4

Federated learning is used to train a shared model in a decentralized way without clients sharing private data with each other. Federated learning systems are susceptible to poison…