Removing Backdoors in Pre-trained Models by Regularized Continual Pre-training TACL

Biru Zhu | Ganqu Cui | Yangyi Chen | Yujia Qin | Lifan Yuan | Chong Fu | Yangdong Deng | Zhiyuan Liu | Maosong Sun | Ming Gu |

Beat LLMs at Their Own Game: Zero-Shot LLM-Generated Text Detection via Querying ChatGPT EMNLP

Biru Zhu | Lifan Yuan | Ganqu Cui | Yangyi Chen | Chong Fu | Bingxiang He | Yangdong Deng | Zhiyuan Liu | Maosong Sun | Ming Gu |

From Adversarial Arms Race to Model-centric Evaluation: Motivating a Unified Automatic Robustness Evaluation Framework F i n d i n g s - A C L

Yangyi Chen | Hongcheng Gao | Ganqu Cui | Lifan Yuan | Dehan Kong | Hanlu Wu | Ning Shi | Bo Yuan | Longtao Huang | Hui Xue | Zhiyuan Liu | Maosong Sun | Heng Ji |

ViStruct: Visual Structural Knowledge Extraction via Curriculum Guided Code-Vision Representation EMNLP

Yangyi Chen | Xingyao Wang | Manling Li | Derek Hoiem | Heng Ji |

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

Yangyi Chen | Lifan Yuan | Ganqu Cui | Zhiyuan Liu | Heng Ji |

Bridge the Gap Between CV and NLP! A Gradient-based Textual Adversarial Attack Framework F i n d i n g s - A C L

Lifan Yuan | YiChi Zhang | Yangyi Chen | Wei Wei |

Making Pre-trained Language Models both Task-solvers and Self-calibrators F i n d i n g s - A C L

Yangyi Chen | Xingyao Wang | Heng Ji |

Exploring the Universal Vulnerability of Prompt-based Learning Paradigm Findings NAACL

Lei Xu | Yangyi Chen | Ganqu Cui | Hongcheng Gao | Zhiyuan Liu |

Textual Backdoor Attacks Can Be More Harmful via Two Simple Tricks EMNLP

Yangyi Chen | Fanchao Qi | Hongcheng Gao | Zhiyuan Liu | Maosong Sun |

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

Yangyi Chen | Hongcheng Gao | Ganqu Cui | Fanchao Qi | Longtao Huang | Zhiyuan Liu | Maosong Sun |

Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger ACL IJCNLP

Fanchao Qi | Mukai Li | Yangyi Chen | Zhengyan Zhang | Zhiyuan Liu | Yasheng Wang | Maosong Sun |

Automatic Construction of Sememe Knowledge Bases via Dictionaries Findings

Fanchao Qi | Yangyi Chen | Fengyu Wang | Zhiyuan Liu | Xiao Chen | Maosong Sun |

ONION: A Simple and Effective Defense Against Textual Backdoor Attacks EMNLP

Fanchao Qi | Yangyi Chen | Mukai Li | Yuan Yao | Zhiyuan Liu | Maosong Sun |

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

Fanchao Qi | Yangyi Chen | Xurui Zhang | Mukai Li | Zhiyuan Liu | Maosong Sun |

Multi-granularity Textual Adversarial Attack with Behavior Cloning EMNLP

Yangyi Chen | Jin Su | Wei Wei |