Fanchao Qi

ONION: A Simple and Effective Defense Against Textual Backdoor Attacks

Fanchao Qi, Yangyi Chen, Mukai Li et al. · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · 2021 · 165 citations · Full text

Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger

Fanchao Qi, Mukai Li, Yangyi Chen et al. · 2021 · 132 citations · Full text

Engineering, Information Security, Part-of-speech Tagging +20

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

Fanchao Qi, Yang‐Yi Chen, Xurui Zhang et al. · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · 2021 · 108 citations · Full text

CPM: A large-scale generative Chinese Pre-trained language model

Zhengyan Zhang, Xu Han, Hao Zhou et al. · AI Open · 2021 · 95 citations · Full text

Llm Fine-tuning, Engineering, Machine Learning +19

Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution

Fanchao Qi, Yuan Yao, Sophia Xu et al. · 2021 · 91 citations · Full text

Engineering, Evasion Technique, Information Security +21