Don't be a Fool: Pooling Strategies in Offensive Language Detection from User-Intended Adversarial Attacks

arXiv:2403.15467v1 Announce Type: new
Abstract: Offensive language detection is an important task for filtering out abusive expressions and improving online user experiences. However, malicious users often attempt to avoid filtering systems through the involvement of textual noises. In this paper, we propose these evasions as user-intended adversarial attacks that insert special symbols or leverage the distinctive features of the Korean language. Furthermore, we introduce simple yet effective pooling strategies in a layer-wise manner to defend against the proposed attacks, focusing …

abstract adversarial adversarial attacks arxiv attacks cs.cl detection filtering however improving language paper pooling strategies systems textual through type