Red Alarm for Pre-trained Models: Universal Vulnerabilities by Neuron-Level Backdoor Attacks

By Zhengyan Zhang, Guangxuan Xiao, Yongwei Li, Tian Lv, Fanchao Qi, Zhiyuan Liu, Yasheng Wang, Xin Jiang, Maosong Sun. 2021

15 citations recorded by the source corpus.

Citations in the corpus

• Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models (2021, unknown): “on downstream task-specific datasets (Kurita et al., 2020; Zhang et al., 2021).”