most citedSet-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models

2 citations · 2 across the 2 of their papers we have counts for

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2023★ 2 cited

Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models

Dong Lu, Zhiqiang Wang, Teng Wang +3

Vision-language pre-training (VLP) models have shown vulnerability to adversarial examples in multimodal tasks. Furthermore, malicious adversaries can be deliberately transferred t…