<ul><li>Toxicity detection is crucial for maintaining the peace of the society.</li><li>Existing methods are vulnerable to evolving perturbation patterns created by malicious users.</li><li>A new dataset with 9 types of perturbation patterns has been constructed to validate the vulnerability of current methods.</li><li>A domain incremental learning paradigm and benchmark are proposed to ensure robustness to dynamically emerging types of perturbed toxic text.</li></ul>

Toxicity Detection towards Adaptability to Changing Perturbations

Discover more