Global ETD Search

Defending Against Trojan Attacks on Neural Network-based Language Models

Azizi, AhmadrezaVirginia Tech2020

… a certain pattern to a portion of given training dataset, causing the DNN model to misclassify any inputs that contain the pattern. These infected classifiers are called Trojan models and the added pattern is referred to as the trigger. In image domain, a trigger can be a patch of pixel values …

vt Repository record for Defending Against Trojan Attacks on Neural Network-based Language Models (opens in a new tab)