Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models

Christian Schlarmann; Naman Deep Singh; Francesco Croce; Matthias Hein

2024 ICML ICML 2024

Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🐣 Hot Topic Early Bird - vision encoder

Authors

Christian Schlarmann, Naman Deep Singh, Francesco Croce, Matthias Hein

Topics

Artificial Intelligence > Core AI > Foundation Models Machine Learning > Learning Types > Adversarial Learning Deep Learning > Learning Types > Multimodal Learning

Keywords

robustness large vision-language model vision encoder adversarial fine-tuning clip stealth-attacks

Download PDF