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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

A Close Look into the Calibration of Pre-trained Language Models


Oct 31, 2022
Yangyi Chen, Lifan Yuan, Ganqu Cui, Zhiyuan Liu, Heng Ji

Add code

* Code is available at: https://github.com/lifan-yuan/PLMCalibration 

   Access Paper or Ask Questions

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

Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLP


Oct 19, 2022
Yangyi Chen, Hongcheng Gao, Ganqu Cui, Fanchao Qi, Longtao Huang, Zhiyuan Liu, Maosong Sun

Add code

* Accepted to EMNLP 2022, main conference 

   Access Paper or Ask Questions

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

A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks


Jun 17, 2022
Ganqu Cui, Lifan Yuan, Bingxiang He, Yangyi Chen, Zhiyuan Liu, Maosong Sun

Add code

* 19 pages 

   Access Paper or Ask Questions

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

Exploring the Universal Vulnerability of Prompt-based Learning Paradigm


Apr 11, 2022
Lei Xu, Yangyi Chen, Ganqu Cui, Hongcheng Gao, Zhiyuan Liu

Add code

* Accepted to Findings of NAACL 2022 

   Access Paper or Ask Questions

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

Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack Framework


Nov 16, 2021
Lifan Yuan, Yichi Zhang, Yangyi Chen, Wei Wei

Add code

* Work on progress 

   Access Paper or Ask Questions

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

Textual Backdoor Attacks Can Be More Harmful via Two Simple Tricks


Oct 15, 2021
Yangyi Chen, Fanchao Qi, Zhiyuan Liu, Maosong Sun

Add code

* Work in progress 

   Access Paper or Ask Questions

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

Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer


Oct 14, 2021
Fanchao Qi, Yangyi Chen, Xurui Zhang, Mukai Li, Zhiyuan Liu, Maosong Sun

Add code

* Accepted by the main conference of EMNLP 2021 as a long paper. The camera-ready version 

   Access Paper or Ask Questions

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

Multi-granularity Textual Adversarial Attack with Behavior Cloning


Sep 09, 2021
Yangyi Chen, Jin Su, Wei Wei

Add code

* Accepted by the main conference of 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

Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger


Jun 03, 2021
Fanchao Qi, Mukai Li, Yangyi Chen, Zhengyan Zhang, Zhiyuan Liu, Yasheng Wang, Maosong Sun

Add code

* Accepted by ACL-IJCNLP 2021 as a long paper. Camera-ready version 

   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
>>