paper-with-me

Papers

Insta-RS: Instance-wise Randomized Smoothing for Improved Robustness and Accuracy

2021-03-07 · Chen Chen, Kezhi Kong, Peihong Yu, Juan Luque, Tom Goldstein, Furong Huang

Randomized smoothing (RS) is an effective and scalable technique for constructing neural network classifiers that are certifiably robust to adversarial perturbations. Most RS works focus on training a good base model that boosts the certified robustness of the smoothed model. However, existing RS techniques treat every data point the same, i.e., the variance of the Gaussian noise used to form the smoothed model is preset and universal for all training and test data. This preset and universal Gaussian noise variance is suboptimal since different data points have different margins and the local properties of the base model vary across the input examples. In this paper, we examine the impact of customized handling of examples and propose Instance-wise Randomized Smoothing (Insta-RS) -- a multiple-start search algorithm that assigns customized Gaussian variances to test examples. We also design Insta-RS Train -- a novel two-stage training algorithm that adaptively adjusts and customizes the noise level of each training example for training a base model that boosts the certified robustness of the instance-wise Gaussian smoothed model. Through extensive experiments on CIFAR-10 and ImageNet, we show that our method significantly enhances the average certified radius (ACR) as well as the clean data accuracy compared to existing state-of-the-art provably robust classifiers.

📄 PDF Abstract BibTeX arXiv:2103.04436

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Randomized Smoothing 설명 없음

Similar Papers 제목 키워드 기반

Certified Adversarial Robustness via Anisotropic Randomized Smoothing

2022-07-12 · Hanbin Hong, Yuan Hong

Randomized smoothing has achieved great success for certified robustness against adversarial perturbations. Given any arbitrary classifier, randomized smoothing can guarantee the classifier's prediction over the perturbe…

Adversarial RobustnessAll

Variational Randomized Smoothing for Sample-Wise Adversarial Robustness

2024-07-16 · Ryo Hase, Ye Wang, Toshiaki Koike-Akino, Jing Liu 외

Randomized smoothing is a defensive technique to achieve enhanced robustness against adversarial examples which are small input perturbations that degrade the performance of neural network models. Conventional randomized…

Adversarial Robustness

Instance-based Label Smoothing For Better Calibrated Classification Networks

2021-10-11 · Mohamed Maher, Meelis Kull

Label smoothing is widely used in deep neural networks for multi-class classification. While it enhances model generalization and reduces overconfidence by aiming to lower the probability for the predicted class, it dist…

Classificationimage-classificationImage ClassificationMulti-class Classification

Robustness Evaluation and Adversarial Training of an Instance Segmentation Model

2022-06-02 · Jacob Bond, Andrew Lingg

To evaluate the robustness of non-classifier models, we propose probabilistic local equivalence, based on the notion of randomized smoothing, as a way to quantitatively evaluate the robustness of an arbitrary function. I…

Instance SegmentationLane DetectionSemantic Segmentation

Improved, Deterministic Smoothing for L_1 Certified Robustness

2021-03-17 · Alexander Levine, Soheil Feizi

Randomized smoothing is a general technique for computing sample-dependent robustness guarantees against adversarial attacks for deep classifiers. Prior works on randomized smoothing against L_1 adversarial attacks use a…