Universal Adversarial Perturbations for Vision-Language Pre-trained Models
Peng-Fei Zhang, Zi Huang, Guangdong Bai
Abstract
Vision-language pre-trained (VLP) models have been the foundation of numerous vision-language tasks. Given their prevalence, it becomes imperative to assess their adversarial robustness, especially when deploying them in security-crucial real-world applications. Traditionally, adversarial perturbations generated for this assessment target specific VLP models, datasets, and/or downstream tasks. This practice suffers from low transferability and additional computation costs when transitioning to new scenarios.
Topics & Concepts
Adversarial systemComputer scienceArtificial intelligenceNatural language processingComputer visionAdversarial Robustness in Machine LearningMultimodal Machine Learning ApplicationsDomain Adaptation and Few-Shot Learning