Showing 2024Show all
2 papers · 1 filter
cs.CV2024
EmoAttack: Emotion-to-Image Diffusion Models for Emotional Backdoor Generation
Tianyu Wei, Shanmin Pang, Qi Guo +3
Text-to-image diffusion models can generate realistic images based on textual inputs, enabling users to convey their opinions visually through language. Meanwhile, within language,…
cs.CV2024
Efficient Generation of Targeted and Transferable Adversarial Examples for Vision-Language Models Via Diffusion Models
Qi Guo, Shanmin Pang, Xiaojun Jia +2
Adversarial attacks, particularly \textbf{targeted} transfer-based attacks, can be used to assess the adversarial robustness of large visual-language models (VLMs), allowing for a…