Author

Chia-Yi Hsu

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning May 2026

Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent Skills

Neutral Prompting Attack (NPA), a highly stealthy attack paradigm in which semantically benign instructions, such as encouraging imagination and exhaustiveness, increase package hallucination propensity without containing explicit malicious intent is introduced.

Chia-Yi Hsu, Chi-Yu Li, Chun-Ying Huang et al. · arXiv.org · 1 citation