← Search

Yangshijie Zhang

2 accepted papers

2026

STYLE ATTACK DISGUISE: WHEN FONTS BECOME A CAMOUFLAGE FOR ADVERSARIAL INTENT

ICASSP 2026poster

With social media growth, users employ stylistic fonts and font-like emoji to express individuality, creating visually appealing text that remains human-readable. However, these fonts introduce hidden vulnerabilities in NLP models: while humans easily read stylistic text, models process these charac…

Cited by 0SourcePDFScholar
2025

Multi-task Adversarial Attacks against Black-box Model with Few-shot Queries

ACL 2025long

Current multi-task adversarial text attacks rely on abundant access to shared internal features and numerous queries, often limited to a single task type. As a result, these attacks are less effective against practical scenarios involving black-box feedback APIs, limited queries, or multiple task ty…

Cited by 0SourcePDFScholar