Stop reasoning! When multimodal LLMs with chain-of-thought reasoning meets adversarial images
Recently, Multimodal LLMs (MLLMs) have shown a great ability to understand images. However, like traditional vision models, they are still vulnerable to adversarial images. Meanwhile, Chain-of-Thought (CoT) reasoning has been widely explored on MLLMs, which not only improves model’s performance, but...
| Main Authors: | , , , , , , , , |
|---|---|
| 格式: | Conference item |
| 语言: | English |
| 出版: |
IEEE
2024
|