Tight Second-Order Certificates for Randomized Smoothing

by   Alexander Levine, et al.

Randomized smoothing is a popular way of providing robustness guarantees against adversarial attacks: randomly-smoothed functions have a universal Lipschitz-like bound, allowing for robustness certificates to be easily computed. In this work, we show that there also exists a universal curvature-like bound for Gaussian random smoothing: given the exact value and gradient of a smoothed function, we compute a lower bound on the distance of a point to its closest adversarial example, called the Second-order Smoothing (SoS) robustness certificate. In addition to proving the correctness of this novel certificate, we show that SoS certificates are realizable and therefore tight. Interestingly, we show that the maximum achievable benefits, in terms of certified robustness, from using the additional information of the gradient norm are relatively small: because our bounds are tight, this is a fundamental negative result. The gain of SoS certificates further diminishes if we consider the estimation error of the gradient norms, for which we have developed an estimator. We therefore additionally develop a variant of Gaussian smoothing, called Gaussian dipole smoothing, which provides similar bounds to randomized smoothing with gradient information, but with much-improved sample efficiency. This allows us to achieve (marginally) improved robustness certificates on high-dimensional datasets such as CIFAR-10 and ImageNet. Code is available at https://github.com/alevine0/smoothing_second_order.


page 1

page 2

page 3

page 4


Certified Robustness for Top-k Predictions against Adversarial Perturbations via Randomized Smoothing

It is well-known that classifiers are vulnerable to adversarial perturba...

Improved, Deterministic Smoothing for L1 Certified Robustness

Randomized smoothing is a general technique for computing sample-depende...

Curse of Dimensionality on Randomized Smoothing for Certifiable Robustness

Randomized smoothing, using just a simple isotropic Gaussian distributio...

Towards Assessment of Randomized Mechanisms for Certifying Adversarial Robustness

As a certified defensive technique, randomized smoothing has received co...

CROP: Certifying Robust Policies for Reinforcement Learning through Functional Smoothing

We present the first framework of Certifying Robust Policies for reinfor...

Towards Assessment of Randomized Smoothing Mechanisms for Certifying Adversarial Robustness

As a certified defensive technique, randomized smoothing has received co...

Higher-Order Certification for Randomized Smoothing

Randomized smoothing is a recently proposed defense against adversarial ...

Please sign up or login with your details

Forgot password? Click here to reset