One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models

Understand

Vision-Language Pre-training (VLP) models have exhibited unprecedented capability in many applications by taking full advantage of the multimodal alignment.

• However, previous studies have shown they are vulnerable to maliciously crafted adversarial samples.
• Despite recent success, these methods are generally instance-specific and require generating perturbations for each input sample.
• In this paper, we reveal that VLP models are also vulnerable to the instance-agnostic universal adversarial perturbation (UAP).