Towards Assessment of Randomized Mechanisms for Certifying Adversarial Robustness

05/15/2020
by   Tianhang Zheng, et al.
8

As a certified defensive technique, randomized smoothing has received considerable attention due to its scalability to large datasets and neural networks. However, several important questions remain unanswered, such as (i) whether the Gaussian mechanism is an appropriate option for certifying ℓ_2-norm robustness, and (ii) whether there is an appropriate randomized mechanism to certify ℓ_∞-norm robustness on high-dimensional datasets. To shed light on these questions, we introduce a generic framework that connects the existing frameworks to assess randomized mechanisms. Under our framework, we define the magnitude of the noise required by a mechanism to certify a certain extent of robustness as the metric for assessing the appropriateness of the mechanism. We also derive lower bounds on the metric as the criteria for assessment. Assessment of Gaussian and Exponential mechanisms is achieved by comparing the magnitude of noise needed by these mechanisms and the criteria, and we conclude that the Gaussian mechanism is an appropriate option to certify both ℓ_2-norm and ℓ_∞-norm robustness. The veracity of our framework is verified by evaluations on CIFAR10 and ImageNet.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/15/2020

Towards Assessment of Randomized Smoothing Mechanisms for Certifying Adversarial Robustness

As a certified defensive technique, randomized smoothing has received co...
research
02/19/2020

Randomized Smoothing of All Shapes and Sizes

Randomized smoothing is a recently proposed defense against adversarial ...
research
10/20/2020

Tight Second-Order Certificates for Randomized Smoothing

Randomized smoothing is a popular way of providing robustness guarantees...
research
03/02/2020

Rethinking Randomized Smoothing for Adversarial Robustness

The fragility of modern machine learning models has drawn a considerable...
research
11/15/2020

Almost Tight L0-norm Certified Robustness of Top-k Predictions against Adversarial Perturbations

Top-k predictions are used in many real-world applications such as machi...
research
07/31/2019

Adversarial Robustness Curves

The existence of adversarial examples has led to considerable uncertaint...
research
11/21/2021

Randomized FIFO Mechanisms

We study the matching of jobs to workers in a queue, e.g. a ridesharing ...

Please sign up or login with your details

Forgot password? Click here to reset