Chain of Attack: On the Robustness of Vision-Language Models Against Transfer-Based Adversarial Attacks

no code implementations • CVPR 2025 • Peng Xie, Yequan Bie, Jianda Mao, Yangqiu Song, Yang Wang, Hao Chen, Kani Chen

Pre-trained vision-language models (VLMs) have showcased remarkable performance in image and natural language understanding, such as image captioning and response generation.

Image Captioning Natural Language Understanding +1