all AI news
WeDef: Weakly Supervised Backdoor Defense for Text Classification. (arXiv:2205.11803v1 [cs.CL])
May 25, 2022, 1:12 a.m. | Lesheng Jin, Zihan Wang, Jingbo Shang
cs.CL updates on arXiv.org arxiv.org
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
More from arxiv.org / cs.CL updates on arXiv.org
Jobs in AI, ML, Big Data
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Senior AI & Data Engineer
@ Bertelsmann | Kuala Lumpur, 14, MY, 50400
Analytics Engineer
@ Reverse Tech | Philippines - Remote