VertAttack: Taking advantage of Text Classifiers' horizontal vision

arXiv:2404.08538v1 Announce Type: new
Abstract: Text classification systems have continuously improved in performance over the years. However, nearly all current SOTA classifiers have a similar shortcoming, they process text in a horizontal manner. Vertically written words will not be recognized by a classifier. In contrast, humans are easily able to recognize and read words written both horizontally and vertically. Hence, a human adversary could write problematic words vertically and the meaning would still be preserved to other humans. We simulate …

abstract arxiv classification classifier classifiers contrast cs.cl current however humans performance process sota systems text text classification type vision will words