# Robust and Accurate -- Compositional Architectures for Randomized Smoothing Source: [Robust and Accurate -- Compositional Architectures for Randomized Smoothing]() Collection index: [llms.txt]() Data updated: 2025-10-26T00:06:48.603Z Authors: Mikl\\'os Z. Horv\\'ath, Mark Niklas M\\"uller, Marc Fischer, Martin Vechev Published: 2022-04-01T14:46:25.000Z ## Abstract Randomized Smoothing (RS) is considered the state-of-the-art approach to obtain certifiably robust models for challenging tasks. However, current RS approaches drastically decrease standard accuracy on unperturbed data, severely limiting their real-world utility. To address this limitation, we propose a compositional architecture, ACES, which certifiably decides on a per-sample basis whether to use a smoothed model yielding predictions with guarantees or a more accurate standard model without guarantees. This, in contrast to prior approaches, enables both high standard accuracies and significant provable robustness. On challenging tasks such as ImageNet, we obtain, e.g., $80.0\\%$ natural accuracy and $28.2\\%$ certifiable accuracy against $\\ell\_2$ perturbations with $r=1.0$. We release our code and models at https://github.com/eth-sri/aces. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()