OpenBackdoor
byTHUNLP
An open-source toolkit for textual backdoor attack and defense (NeurIPS 2022 D&B, Spotlight)
NLP & Text AnalysisOpen Source AI & Machine LearningOpen Source
About
OpenBackdoor is an open-source toolkit for textual backdoor attack and defense, which enables easy implementation, evaluation, and extension of both attack and defense models.
Open Source Health
- Stars
- 211
- Forks
- 27
- License
- Apache-2.0
- Last commit
- 4 years ago
Python
Alternatives to OpenBackdoor
- TAADpapersby THUNLPMust-read Papers on Textual Adversarial Attack and Defense
Textrankby Summa NLPTextRank implementation for Python 3.
KoBERTby SK T-BrainKorean BERT pre-trained cased (KoBERT)
AutoPhraseby Jingbo ShangAutoPhrase: Automated Phrase Mining from Massive Text Corpora
Recognizers-Textby MicrosoftRecognizers-Text offers entity recognition and resolution for numbers, dates, and units in multiple languages.
Resources & Links
Related Categories
Using OpenBackdoor?
Track its cost next to the rest of your stack and get a reminder before it renews.
Add to my stackVendor
THUNLP
Natural Language Processing Lab at Tsinghua University
