Are BERT-based fact-checking models robust against adversarial attack?

More Info


We seek to examine the vulnerability of BERT-based fact-checking. We implement a gradient based, adversarial attack strategy, based on Hotflip swapping individual tokens from the input. We use this on a pre-trained ExPred model for fact-checking. We find that gradient based adversarial attacks are ineffective against ExPred. Uncertainties about the similitude of the examples generated by our adversarial attack implementation cast doubts on the results.


(.pdf | 0.308 Mb)