Are Synonym Substitution Attacks Really Synonym Substitution Attacks?
Journal
Proceedings of the Annual Meeting of the Association for Computational Linguistics
ISBN
9781959429623
Date Issued
2023-01-01
Author(s)
Chiang, Cheng Han
Abstract
In this paper, we explore the following question: Are synonym substitution attacks really synonym substitution attacks (SSAs)? We approach this question by examining how SSAs replace words in the original sentence and show that there are still unresolved obstacles that make current SSAs generate invalid adversarial samples. We reveal that four widely used word substitution methods generate a large fraction of invalid substitution words that are ungrammatical or do not preserve the original sentence's semantics. Next, we show that the semantic and grammatical constraints used in SSAs for detecting invalid word replacements are highly insufficient in detecting invalid adversarial samples.
Type
conference paper