Robustness Analysis of Grover for Machine-Generated News Detection
Rinaldo Gagiano | Maria Myung-Hee Kim | Xiuzhen Zhang | Jennifer Biggs
Proceedings of the The 19th Annual Workshop of the Australasian Language Technology Association
Advancements in Natural Language Generation have raised concerns on its potential misuse for deep fake news. Grover is a model for both generation and detection of neural fake news. While its performance on automatically discriminating neural fake news surpassed GPT-2 and BERT, Grover could face a variety of adversarial attacks to deceive detection. In this work, we present an investigation of Groverâs susceptibility to adversarial attacks such as character-level and word-level perturbations. The experiment results show that even a singular character alteration can cause Grover to fail, affecting up to 97% of target articles with unlimited attack attempts, exposing a lack of robustness. We further analyse these misclassified cases to highlight affected words, identify vulnerability within Groverâs encoder, and perform a novel visualisation of cumulative classification scores to assist in interpreting model behaviour.