[Re] Double Sampling Randomized Smoothing

Author name not available (Why is that?)

Publication date: 27 June 2023

Abstract: This paper is a contribution to the reproducibility challenge in the field of machine learning, specifically addressing the issue of certifying the robustness of neural networks (NNs) against adversarial perturbations. The proposed Double Sampling Randomized Smoothing (DSRS) framework overcomes the limitations of existing methods by using an additional smoothing distribution to improve the robustness certification. The paper provides a clear manifestation of DSRS for a generalized family of Gaussian smoothing and a computationally efficient method for implementation. The experiments on MNIST and CIFAR-10 demonstrate the effectiveness of DSRS, consistently certifying larger robust radii compared to other methods. Also various ablations studies are conducted to further analyze the hyperparameters and effect of adversarial training methods on the certified radius by the proposed framework.

Has companion code repository: https://github.com/dsgiitr/re_dsrs

This page was built for publication: [Re] Double Sampling Randomized Smoothing

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6441619)