Skip to yearly menu bar Skip to main content


In-Person Poster presentation / poster accept

Sound Randomized Smoothing in Floating-Point Arithmetic

Vaclav Voracek · Matthias Hein

MH1-2-3-4 #136

Keywords: [ adversarial robustness ] [ floating-point arithmetic ] [ formal methods ] [ Randomized Smoothing ] [ Social Aspects of Machine Learning ]


Abstract: Randomized smoothing is sound when using infinite precision. However, we show that randomized smoothing is no longer sound for limited floating-point precision. We present a simple example where randomized smoothing certifies a radius of $1.26$ around a point, even though there is an adversarial example in the distance $0.8$ and show how this can be abused to give false certificates for CIFAR10. We discuss the implicit assumptions of randomized smoothing and show that they do not apply to generic image classification models whose smoothed versions are commonly certified. In order to overcome this problem, we propose a sound approach to randomized smoothing when using floating-point precision with essentially equal speed for quantized input. It yields sound certificates or image classifiers which for the ones tested so far are very similar to the unsound practice of randomized smoothing. Our only assumption is that we have access to a fair coin.

Chat is not available.