Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

A General Framework for Defending Against Backdoor Attacks via Influence Graph


Nov 29, 2021
Xiaofei Sun, Jiwei Li, Xiaoya Li, Ziyao Wang, Tianwei Zhang, Han Qiu, Fei Wu, Chun Fan


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Triggerless Backdoor Attack for NLP Tasks with Clean Labels


Nov 15, 2021
Leilei Gan, Jiwei Li, Tianwei Zhang, Xiaoya Li, Yuxian Meng, Fei Wu, Shangwei Guo, Chun Fan

* 8 pages, 2 figures, 6 tables 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models


Oct 06, 2021
Kangjie Chen, Yuxian Meng, Xiaofei Sun, Shangwei Guo, Tianwei Zhang, Jiwei Li, Chun Fan


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Paraphrase Generation as Unsupervised Machine Translation


Sep 07, 2021
Chun Fan, Yufei Tian, Yuxian Meng, Nanyun Peng, Xiaofei Sun, Fei Wu, Jiwei Li


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

$k$Folden: $k$-Fold Ensemble for Out-Of-Distribution Detection


Aug 29, 2021
Xiaoya Li, Jiwei Li, Xiaofei Sun, Chun Fan, Tianwei Zhang, Fei Wu, Yuxian Meng, Jun Zhang

* To appear at EMNLP 2021 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Layer-wise Model Pruning based on Mutual Information


Aug 28, 2021
Chun Fan, Jiwei Li, Xiang Ao, Fei Wu, Yuxian Meng, Xiaofei Sun

* To appear at EMNLP2021 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Defending against Backdoor Attacks in Natural Language Generation


Jun 03, 2021
Chun Fan, Xiaoya Li, Yuxian Meng, Xiaofei Sun, Xiang Ao, Fei Wu, Jiwei Li, Tianwei Zhang


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Parameter Estimation for the SEIR Model Using Recurrent Nets


May 30, 2021
Chun Fan, Yuxian Meng, Xiaofei Sun, Fei Wu, Tianwei Zhang, Jiwei Li


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Dependency Parsing as MRC-based Span-Span Prediction


May 17, 2021
Leilei Gan, Yuxian Meng, Kun Kuang, Xiaofei Sun, Chun Fan, Fei Wu, Jiwei Li


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Sentence Similarity Based on Contexts


May 17, 2021
Xiaofei Sun, Yuxian Meng, Xiang Ao, Fei Wu, Tianwei Zhang, Jiwei Li, Chun Fan


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
>>