2052b3e0617ecb2ce9474a6feaf422b3-Paper-Datasets_and_Benchmarks.pdf

Neural Information Processing Systems 

Textual backdoor attacks are a kind of practical threat to NLP systems. By injecting a backdoor in the training phase, the adversary could control model predictions via predefined triggers.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found