Preserving Semantics in Textual Adversarial Attacks
This addresses the need for better adversarial attacks to strengthen hate speech detection systems, though it is incremental as it builds on existing methods.
The paper tackles the problem of adversarial attacks on text classifiers by showing that up to 70% of generated adversarial examples fail to preserve semantics, and proposes a new supervised sentence embedding technique (SPE) that improves real attack success rates by 1.2x to 5.1x.
The growth of hateful online content, or hate speech, has been associated with a global increase in violent crimes against minorities [23]. Harmful online content can be produced easily, automatically and anonymously. Even though, some form of auto-detection is already achieved through text classifiers in NLP, they can be fooled by adversarial attacks. To strengthen existing systems and stay ahead of attackers, we need better adversarial attacks. In this paper, we show that up to 70% of adversarial examples generated by adversarial attacks should be discarded because they do not preserve semantics. We address this core weakness and propose a new, fully supervised sentence embedding technique called Semantics-Preserving-Encoder (SPE). Our method outperforms existing sentence encoders used in adversarial attacks by achieving 1.2x - 5.1x better real attack success rate. We release our code as a plugin that can be used in any existing adversarial attack to improve its quality and speed up its execution.