VertAttack: Taking advantage of Text Classifiers' horizontal vision
This exposes a security flaw in text classifiers that could be exploited by human adversaries, highlighting the need for more robust algorithms.
The paper tackles the vulnerability of text classifiers to vertical text by introducing VertAttack, which identifies key words and rewrites them vertically, causing accuracy drops such as reducing RoBERTa's performance on SST2 from 94% to 13%.
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 such an attack, VertAttack. VertAttack identifies which words a classifier is reliant on and then rewrites those words vertically. We find that VertAttack is able to greatly drop the accuracy of 4 different transformer models on 5 datasets. For example, on the SST2 dataset, VertAttack is able to drop RoBERTa's accuracy from 94 to 13%. Furthermore, since VertAttack does not replace the word, meaning is easily preserved. We verify this via a human study and find that crowdworkers are able to correctly label 77% perturbed texts perturbed, compared to 81% of the original texts. We believe VertAttack offers a look into how humans might circumvent classifiers in the future and thus inspire a look into more robust algorithms.