Exploring Semantic Perturbations on Grover
This work addresses the problem of improving fake news detection for the public by identifying weaknesses in an existing model, but it is incremental as it focuses on testing rather than proposing a new solution.
The authors tested Grover's fake news detection by performing targeted adversarial attacks on input news articles, exposing vulnerabilities that need addressing for accurate detection.
With news and information being as easy to access as they currently are, it is more important than ever to ensure that people are not mislead by what they read. Recently, the rise of neural fake news (AI-generated fake news) and its demonstrated effectiveness at fooling humans has prompted the development of models to detect it. One such model is the Grover model, which can both detect neural fake news to prevent it, and generate it to demonstrate how a model could be misused to fool human readers. In this work we explore the Grover model's fake news detection capabilities by performing targeted attacks through perturbations on input news articles. Through this we test Grover's resilience to these adversarial attacks and expose some potential vulnerabilities which should be addressed in further iterations to ensure it can detect all types of fake news accurately.