Add pipeline tag and library name
#1
by
nielsr
HF Staff
- opened
README.md
CHANGED
|
@@ -1,7 +1,9 @@
|
|
| 1 |
---
|
| 2 |
-
license: mit
|
| 3 |
datasets:
|
| 4 |
- Jarvis1111/RobustVLGuard
|
|
|
|
|
|
|
|
|
|
| 5 |
---
|
| 6 |
|
| 7 |
# 🚀 Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks
|
|
@@ -18,9 +20,11 @@ We propose state-of-the-art solutions to enhance the robustness of Vision-Langua
|
|
| 18 |
|
| 19 |
- 🎯 **Robust-VLGuard**: A pioneering multimodal safety dataset covering both aligned and misaligned image-text pair scenarios.
|
| 20 |
|
|
|
|
| 21 |
|
| 22 |
- 🛡️ **DiffPure-VLM**: A novel defense framework that leverages diffusion models to neutralize adversarial noise by transforming it into Gaussian-like noise, significantly improving VLM resilience.
|
| 23 |
|
|
|
|
| 24 |
|
| 25 |
---
|
| 26 |
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
datasets:
|
| 3 |
- Jarvis1111/RobustVLGuard
|
| 4 |
+
license: mit
|
| 5 |
+
pipeline_tag: image-text-to-text
|
| 6 |
+
library_name: transformers
|
| 7 |
---
|
| 8 |
|
| 9 |
# 🚀 Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks
|
|
|
|
| 20 |
|
| 21 |
- 🎯 **Robust-VLGuard**: A pioneering multimodal safety dataset covering both aligned and misaligned image-text pair scenarios.
|
| 22 |
|
| 23 |
+
|
| 24 |
|
| 25 |
- 🛡️ **DiffPure-VLM**: A novel defense framework that leverages diffusion models to neutralize adversarial noise by transforming it into Gaussian-like noise, significantly improving VLM resilience.
|
| 26 |
|
| 27 |
+
|
| 28 |
|
| 29 |
---
|
| 30 |
|