4 papers
Red-Teaming Text-to-Image Models via In-Context Experience Replay and Semantic-Preserving Prompt Rewriting
Zhi-Yi Chin, Pin-Yu Chen, Wei-Chen Chiu +1
Understanding the capabilities of text-to-image (T2I) models in harmful content generation is essential to safety and compliance. However, human red-teaming is costly and inconsist…
MENTOR: Multilingual tExt detectioN TOward leaRning by analogy
Hsin-Ju Lin, Tsu-Chun Chung, Ching-Chun Hsiao +3
Text detection is frequently used in vision-based mobile robots when they need to interpret texts in their surroundings to perform a given task. For instance, delivery robots in mu…
Masking Improves Contrastive Self-Supervised Learning for ConvNets, and Saliency Tells You Where
Zhi-Yi Chin, Chieh-Ming Jiang, Ching-Chun Huang +2
While image data starts to enjoy the simple-but-effective self-supervised learning scheme built upon masking and self-reconstruction objective thanks to the introduction of tokeniz…
Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts
Zhi-Yi Chin, Chieh-Ming Jiang, Ching-Chun Huang +2
Text-to-image diffusion models, e.g. Stable Diffusion (SD), lately have shown remarkable ability in high-quality content generation, and become one of the representatives for the r…