paper-with-me

Papers

Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers

2019-06-09 · NeurIPS 2019 12 · Hadi Salman, Greg Yang, Jerry Li, Pengchuan Zhang, huan zhang, Ilya Razenshteyn, Sebastien Bubeck

Recent works have shown the effectiveness of randomized smoothing as a scalable technique for building neural network-based classifiers that are provably robust to $\ell_2$-norm adversarial perturbations. In this paper, we employ adversarial training to improve the performance of randomized smoothing. We design an adapted attack for smoothed classifiers, and we show how this attack can be used in an adversarial training setting to boost the provable robustness of smoothed classifiers. We demonstrate through extensive experimentation that our method consistently outperforms all existing provably $\ell_2$-robust classifiers by a significant margin on ImageNet and CIFAR-10, establishing the state-of-the-art for provable $\ell_2$-defenses. Moreover, we find that pre-training and semi-supervised learning boost adversarially trained smoothed classifiers even further. Our code and trained models are available at http://github.com/Hadisalman/smoothing-adversarial .

📄 PDF Abstract BibTeX arXiv:1906.04584

Code (3)

Hadisalman/smoothing-adversarial 공식 구현 pytorch
akshaymehra24/poisoning_certified_defenses tf
azshue/boosting_robust pytorch

Tasks

Adversarial AttackAdversarial DefenseDeep Learning

Methods 이 논문이 사용한 방법론

Randomized Smoothing 설명 없음

Similar Papers 제목 키워드 기반

Exploiting Safe Spots in Neural Networks for Preemptive Robustness and Out-of-Distribution Detection

2021-01-01 · Seungyong Moon, Gaon An, Hyun Oh Song

Recent advances on adversarial defense mainly focus on improving the classifier’s robustness against adversarially perturbed inputs. In this paper, we turn our attention from classifiers to inputs and explore if there ex…

Adversarial DefenseOut-of-Distribution Detection

Confidence-aware Training of Smoothed Classifiers for Certified Robustness

2022-12-18 · Jongheon Jeong, Seojin Kim, Jinwoo Shin

Any classifier can be "smoothed out" under Gaussian noise to build a new classifier that is provably robust to $\ell_2$-adversarial perturbations, viz., by averaging its predictions over the noise via randomized smoothin…

Adversarial Robustness

MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radius

2020-01-08 · ICLR 2020 1 · Runtian Zhai, Chen Dan, Di He, huan zhang 외

Adversarial training is one of the most popular ways to learn robust models but is usually attack-dependent and time costly. In this paper, we propose the MACER algorithm, which learns robust models without using adversa…

Provably Adversarially Robust Nearest Prototype Classifiers

2022-07-14 · Václav Voráček, Matthias Hein

Nearest prototype classifiers (NPCs) assign to each input point the label of the nearest prototype with respect to a chosen distance metric. A direct advantage of NPCs is that the decisions are interpretable. Previous wo…

image-classificationImage Classification

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

2021-03-07 · Chen Chen, Kezhi Kong, Peihong Yu, Juan Luque 외

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 tha…