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.
Neural Information Processing Systems
Feb-7-2026, 20:44:42 GMT