← Search

Chaelyn Lee

1 accepted papers

2025

BitAbuse: A Dataset of Visually Perturbed Texts for Defending Phishing Attacks

NAACL 2025findings

Phishing often targets victims through visually perturbed texts to bypass security systems. The noise contained in these texts functions as an adversarial attack, designed to deceive language models and hinder their ability to accurately interpret the content. However, since it is difficult to obtai…