Forging the Forger: An Attempt to Improve Authorship Verification via Data Augmentation

arXiv:2403.11265v1 Announce Type: new
Abstract: Authorship Verification (AV) is a text classification task concerned with inferring whether a candidate text has been written by one specific author or by someone else. It has been shown that many AV systems are vulnerable to adversarial attacks, where a malicious author actively tries to fool the classifier by either concealing their writing style, or by imitating the style of another author. In this paper, we investigate the potential benefits of augmenting the classifier …

abstract adversarial adversarial attacks arxiv attacks augmentation author classification cs.ai cs.cl cs.lg data systems text text classification type verification via vulnerable