Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks
Published in EMNLP, 2022
Sishuo Chen, Wenkai Yang, Zhiyuan Zhang, Xiaohan Bi, Xu Sun
Publications
Well-classified Examples are Underestimated in Classification with Deep Neural Networks
Published in AAAI, 2022
Guangxiang Zhao, Wenkai Yang, Xuancheng Ren, Lei Li, Yunfang Wu, Xu Sun
[url, arxiv, code]
RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models
Published in EMNLP, 2021
Wenkai Yang, Yankai Lin, Peng Li, Jie Zhou, Xu Sun
[url, arxiv, code]
Rethinking Stealthiness of Backdoor Attack against NLP Models
Published in ACL-IJCNLP, 2021
Wenkai Yang, Yankai Lin, Peng Li, Jie Zhou, Xu Sun
[url, code]
Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models
Published in NAACL-HLT, 2021
Wenkai Yang, Lei Li, Zhiyuan Zhang, Xuancheng Ren, Xu Sun, Bin He
[url, arxiv, code]