Adversarial Examples Against a BERT ABSA Model – Fooling Bert With L33T, Misspellign, and Punctuation,

Abstract

The BERT model is de facto state-of-the-art for aspect-based sentiment analysis (ABSA), an important task in natural language processing. Similar to every other model based on deep learning, BERT is vulnerable to so-called adversarial examples: strategically modified inputs that cause a change in the model’s prediction of the underlying input. In this paper we propose three new methods to create character-level adversarial examples against BERT and evaluate their effectiveness on the ABSA task. Specifically, our attack methods mimic human behavior and use leetspeak, common misspellings, or misplaced commas. By concentrating these changes on important words, we are able to maximize misclassification rates with minimal changes. To the best of our knowledge, we are the first to look into adversarial examples for the ABSA task and the first to propose these attacks.