Distributed Black-box Attack against Image Classification Cloud Services. (arXiv:2210.16371v2 [cs.LG] UPDATED)

Black-box adversarial attacks can fool image classifiers into misclassifying
images without requiring access to model structure and weights. Recently
proposed black-box attacks can achieve a success rate of more than 95% after
less than 1,000 queries. The question then arises of whether black-box attacks
have become a real threat against IoT devices that rely on cloud APIs to
achieve image classification. To shed some light on this, note that prior
research has primarily focused on increasing the success rate and …

arxiv classification cloud cloud services distributed image services