Estimating the Robustness Radius for Randomized Smoothing with 100$\times$ Sample Efficiency

arXiv:2404.17371v1 Announce Type: new
Abstract: Randomized smoothing (RS) has successfully been used to improve the robustness of predictions for deep neural networks (DNNs) by adding random noise to create multiple variations of an input, followed by deciding the consensus. To understand if an RS-enabled DNN is effective in the sampled input domains, it is mandatory to sample data points within the operational design domain, acquire the point-wise certificate regarding robustness radius, and compare it with pre-defined acceptance criteria. Consequently, ensuring …

abstract arxiv consensus create cs.cv cs.lg dnn efficiency multiple networks neural networks noise predictions random robustness sample type