94 citations · 237 across the 12 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.CL2023★ 3 cited
NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models
Kai Mei, Zheng Li, Zhenting Wang +2
Prompt-based learning is vulnerable to backdoor attacks. Existing backdoor attacks against prompt-based models consider injecting backdoors into the entire embedding layers or word…
cs.LG2023★ 7 cited
UNICORN: A Unified Backdoor Trigger Inversion Framework
Zhenting Wang, Kai Mei, Juan Zhai +1
The backdoor attack, where the adversary uses inputs stamped with triggers (e.g., a patch) to activate pre-planted malicious behaviors, is a severe threat to Deep Neural Network (D…