most citedBDMMT: Backdoor Sample Detection for Language Models through Model Mutation Testing

1 citations · 1 across the 1 of their papers we have counts for

collaborators

1 paper

cs.CL2023★ 1 cited

BDMMT: Backdoor Sample Detection for Language Models through Model Mutation Testing

Jiali Wei, Ming Fan, Wenjing Jiao +2

Deep neural networks (DNNs) and natural language processing (NLP) systems have developed rapidly and have been widely used in various real-world fields. However, they have been sho…