Universal Adversarial Perturbations for Vision-Language Pre-trained Models

arXiv:2405.05524v1 Announce Type: new
Abstract: Vision-language pre-trained (VLP) models have been the foundation of numerous vision-language tasks. Given their prevalence, it be- comes 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.
In this work, we thoroughly investigate whether VLP models are commonly sensitive to …

abstract adversarial applications arxiv assessment cs.cv cs.mm datasets foundation generated language pre-trained models robustness security tasks them type universal vision vision-language world