Условный автоэнкодер с противоречивой регуляризацией
method
ID: conditionaladversariallyregularizedautoencoder
Related Papers
Poison Attacks against Text Datasets with Conditional Adversarially Regularized Autoencoder
AbstractThis paper demonstrates a fatal vulnerability in natural language inference (NLI) and text classification systems. More concretely, we present a ‘backdoor poisoning’ attack on NLP models. Our poisoning attack utilizes …...