Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defences
We propose Adaptive Randomized Smoothing (ARS) to certify the predictions of our test-time adaptive models against adversarial examples. ARS extends the analysis of randomized smoothing using $f$-Differential Privacy to certify the adaptive composition of multiple steps. For the first time, our theory covers the sound adaptive composition of general and high-dimensional functions of noisy inputs. We instantiate ARS on deep image classification to certify predictions against adversarial examples of bounded $L_{\infty}$ norm. In the $L_{\infty}$ threat model, ARS enables flexible adaptation through high-dimensional input-dependent masking. We design adaptivity benchmarks, based on CIFAR-10 and CelebA, and show that ARS improves standard test accuracy by $1$ to $15\%$ points. On ImageNet, ARS improves certified test accuracy by up to $1.6\%$ points over standard RS without adaptivity. Our code is available at https://github.com/ubc-systopia/adaptive-randomized-smoothing .
Code (1)
Tasks
Adversarial Robustnessimage-classificationImage ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Certified Adversarial Robustness via Randomized Smoothing
We show how to turn any classifier that classifies well under Gaussian noise into a new classifier that is certifiably robust to adversarial perturbations under the $\ell_2$ norm. This "randomized smoothing" technique ha…
Adversarial DefenseAdversarial RobustnessRobust classificationCertified Robustness for Top-k Predictions against Adversarial Perturbations via Randomized Smoothing
It is well-known that classifiers are vulnerable to adversarial perturbations. To defend against adversarial perturbations, various certified robustness results have been derived. However, existing certified robustnesses…
Adaptive Diffusion Denoised Smoothing : Certified Robustness via Randomized Smoothing with Differentially Private Guided Denoising Diffusion
We propose Adaptive Diffusion Denoised Smoothing, a method for certifying the predictions of a vision model against adversarial examples, while adapting to the input. Our key insight is to reinterpret a guided denoising …
On Certifying Robustness against Backdoor Attacks via Randomized Smoothing
Backdoor attack is a severe security threat to deep neural networks (DNNs). We envision that, like adversarial examples, there will be a cat-and-mouse game for backdoor attacks, i.e., new empirical defenses are developed…
Backdoor AttackTowards Bridging the gap between Empirical and Certified Robustness against Adversarial Examples
The current state-of-the-art defense methods against adversarial examples typically focus on improving either empirical or certified robustness. Among them, adversarially trained (AT) models produce empirical state-of-th…
Adversarial Robustness