2020
EMNLP
EMNLP 2020
How Effectively Can Machines Defend Against Machine-Generated Fake News? An Empirical Study
Abstract
AbstractWe empirically study the effectiveness of machine-generated fake news detectors by understanding the modelโs sensitivity to different synthetic perturbations during test time. The current machine-generated fake news detectors rely on provenance to determine the veracity of news. Our experiments find that the success of these detectors can be limited since they are rarely sensitive to semantic perturbations and are very sensitive to syntactic perturbations. Also, we would like to open-source our code and believe it could be a useful diagnostic tool for evaluating models aimed at fighting machine-generated fake news.
โ
The Questioner
๐
Interdisciplinary Bridge
โ Artificial Intelligence and Natural Language Processing
๐งญ
Keyword Pioneer
โ synthetic perturbation
๐ฃ
Hot Topic Early Bird
โ misinformation detection
๐
Cross-Pollinator
โ Artificial Intelligence, Computer Science, Computer Vision, Data Science & Analytics, Deep Learning, Healthcare & Medicine, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Security & Privacy, Speech & Audio