← Search

Le Liang

2 accepted papers

2025

Perception-Guided Jailbreak Against Text-to-Image Models

AAAI 2025technical

In recent years, Text-to-Image (T2I) models have garnered significant attention due to their remarkable advancements. However, security concerns have emerged due to their potential to generate inappropriate or Not-Safe-For-Work (NSFW) images. In this paper, inspired by the observation that texts wit…

Cited by 7SourcePDFScholar