About Me

Hi! I am a second-year master sutdent at the Center for Data Science of Peking University. I am a member of LANCO group, and I am fortunate to be advised by Prof. Xu Sun. I am interested in Machine Learning (ML) and Natural Language Processing (NLP). Recently I am working on adversarial learning and backdoor learning problems in NLP.

Education

  • Master student in Data Science (Statistics), Peking University, Sept. 2020 - Now.
  • Visiting student in Statistics, University of California, Berkeley, Jan. 2019 - May 2019.
  • Bachelor in Mathematics and Applied Mathematics (Honors Program), Xi’an Jiaotong University, Sept. 2016 - July 2020.

Internship

  • Research Intern of Wechat AI, Tencent Inc., Jan. 2021 - Now.

Publications

  • RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models
    Wenkai Yang, Yankai Lin, Peng Li, Jie Zhou, Xu Sun
    EMNLP 2021

  • Rethinking Stealthiness of Backdoor Attack against NLP Models
    Wenkai Yang, Yankai Lin, Peng Li, Jie Zhou, Xu Sun
    ACL 2021 [url, code]

  • Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models
    Wenkai Yang, Lei Li, Zhiyuan Zhang, Xuancheng Ren, Xu Sun, Bin He
    NAACL-HLT 2021 [url, arxiv, code]

Contact

Email: wkyang (at) stu (dot) pku (dot) edu (dot) cn