G. M. Shahariar

Adversarial Attacks on Parts of Speech: An Empirical Study in Text-to-Image Generation

2024 · arXiv (Cornell University)

Recent studies show that text-to-image (T2I) models are vulnerable to adversarial attacks, especially with noun perturbations in text prompts. In this study, we investigate the impact of adversarial attacks on different POS tags within text …