WeDef: Weakly Supervised Backdoor Defense for Text Classification. (arXiv:2205.11803v1 [cs.CL])

Existing backdoor defense methods are only effective for limited trigger
types. To defend different trigger types at once, we start from the
class-irrelevant nature of the poisoning process and propose a novel weakly
supervised backdoor defense framework WeDef. Recent advances in weak
supervision make it possible to train a reasonably accurate text classifier
using only a small number of user-provided, class-indicative seed words. Such
seed words shall be considered independent of the triggers. Therefore, a weakly
supervised text classifier trained …

arxiv backdoor classification defense text text classification