RAP: Robustness-Aware Perturbations for Defending against Backdoor Attacks on NLP Models.

Wenkai Yang Yankai Lin Peng Li Jie Zhou Xu Sun

Published in: EMNLP (1) (2021)

Keyphrases

probabilistic model
statistical models
statistical model
neural network
natural language
information extraction
natural language processing
experimental data
parametric models
semi fragile watermarking