Language-Driven Anchors for Zero-Shot Adversarial Robustness

arXiv:2301.13096v3 Announce Type: replace-cross
Abstract: Deep Neural Networks (DNNs) are known to be susceptible to adversarial attacks. Previous researches mainly focus on improving adversarial robustness in the fully supervised setting, leaving the challenging domain of zero-shot adversarial robustness an open question. In this work, we investigate this domain by leveraging the recent advances in large vision-language models, such as CLIP, to introduce zero-shot adversarial robustness to DNNs. We propose LAAT, a Language-driven, Anchor-based Adversarial Training strategy. LAAT utilizes the features …

abstract advances adversarial adversarial attacks anchors arxiv attacks cs.ai cs.cv cs.lg domain focus language networks neural networks question robustness type work zero-shot