3 citations · 3 across the 9 of their papers we have counts for
Showing 2024 · cs.CVShow all
2 papers · 2 filters
cs.CV2024
Multimodal Adversarial Defense for Vision-Language Models by Leveraging One-To-Many Relationships
Futa Waseda, Antonio Tejero-de-Pablos, Isao Echizen
Pre-trained vision-language (VL) models are highly vulnerable to adversarial attacks. However, existing defense methods primarily focus on image classification, overlooking two key…
cs.CV2024
Fine-Tuning Text-To-Image Diffusion Models for Class-Wise Spurious Feature Generation
AprilPyone MaungMaung, Huy H. Nguyen, Hitoshi Kiya +1
We propose a method for generating spurious features by leveraging large-scale text-to-image diffusion models. Although the previous work detects spurious features in a large-scale…