paper-with-me

홈 › Papers

Towards Out-of-Distribution Adversarial Robustness

2022-10-06 · Adam Ibrahim, Charles Guille-Escuret, Ioannis Mitliagkas, Irina Rish, David Krueger, Pouya Bashivan

Adversarial robustness continues to be a major challenge for deep learning. A core issue is that robustness to one type of attack often fails to transfer to other attacks. While prior work establishes a theoretical trade-off in robustness against different $L_p$ norms, we show that there is potential for improvement against many commonly used attacks by adopting a domain generalisation approach. Concretely, we treat each type of attack as a domain, and apply the Risk Extrapolation method (REx), which promotes similar levels of robustness against all training attacks. Compared to existing methods, we obtain similar or superior worst-case adversarial robustness on attacks seen during training. Moreover, we achieve superior performance on families or tunings of attacks only encountered at test time. On ensembles of attacks, our approach improves the accuracy from 3.4% with the best existing baseline to 25.9% on MNIST, and from 16.9% to 23.5% on CIFAR10.

📄 PDF Abstract BibTeX arXiv:2210.03150

Code (1)

aiproj/towards-out-of-distribution-adversarial-robustness 공식 구현 pytorch

Tasks

Adversarial Robustness

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

On the Effects of Adversarial Perturbations on Distribution Robustness

2026-01-23 · Yipei Wang, Zhaoying Pan, Xiaoqian Wang arxiv

Adversarial robustness refers to a model's ability to resist perturbation of inputs, while distribution robustness evaluates the performance of the model under data shifts. Although both aim to ensure reliable performanc…

Adversarial Robustness

OODRobustBench: a Benchmark and Large-Scale Analysis of Adversarial Robustness under Distribution Shift

2023-10-19 · Lin Li, Yifei Wang, Chawin Sitawarin, Michael Spratling

Existing works have made great progress in improving adversarial robustness, but typically test their method only on data from the same distribution as the training data, i.e. in-distribution (ID) testing. As a result, i…

Adversarial RobustnessBenchmarkingData Augmentation

On the Sensitivity of Adversarial Robustness to Input Data Distributions

2019-02-22 · ICLR 2019 5 · Gavin Weiguang Ding, Kry Yik Chau Lui, Xiaomeng Jin, Luyu Wang 외

Neural networks are vulnerable to small adversarial perturbations. Existing literature largely focused on understanding and mitigating the vulnerability of learned models. In this paper, we demonstrate an intriguing phen…

Adversarial RobustnessSensitivity

Adversarial Robustness on In- and Out-Distribution Improves Explainability

2020-03-20 · ECCV 2020 8 · Maximilian Augustin, Alexander Meinke, Matthias Hein

Neural networks have led to major improvements in image classification but suffer from being non-robust to adversarial changes, unreliable uncertainty estimates on out-distribution samples and their inscrutable black-box…

Adversarial Robustnessimage-classificationImage Classification

Long-tailed Adversarial Training with Self-Distillation

2025-03-09 · Seungju Cho, Hongsin Lee, Changick Kim

Adversarial training significantly enhances adversarial robustness, yet superior performance is predominantly achieved on balanced datasets. Addressing adversarial robustness in the context of unbalanced or long-tailed d…

Adversarial Robustness