paper-with-me

Papers

Are Adversarial Robustness and Common Perturbation Robustness Independent Attributes ?

2019-09-04 · Alfred Laugros, Alice Caplier, Matthieu Ospici

Neural Networks have been shown to be sensitive to common perturbations such as blur, Gaussian noise, rotations, etc. They are also vulnerable to some artificial malicious corruptions called adversarial examples. The adversarial examples study has recently become very popular and it sometimes even reduces the term "adversarial robustness" to the term "robustness". Yet, we do not know to what extent the adversarial robustness is related to the global robustness. Similarly, we do not know if a robustness to various common perturbations such as translations or contrast losses for instance, could help with adversarial corruptions. We intend to study the links between the robustnesses of neural networks to both perturbations. With our experiments, we provide one of the first benchmark designed to estimate the robustness of neural networks to common perturbations. We show that increasing the robustness to carefully selected common perturbations, can make neural networks more robust to unseen common perturbations. We also prove that adversarial robustness and robustness to common perturbations are independent. Our results make us believe that neural network robustness should be addressed in a broader sense.

📄 PDF Abstract BibTeX arXiv:1909.02436

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial Robustness

Similar Papers 제목 키워드 기반

Benchmarking Neural Network Robustness to Common Corruptions and Perturbations

2019-03-28 · ICLR 2019 5 · Dan Hendrycks, Thomas Dietterich

In this paper we establish rigorous benchmarks for image classifier robustness. Our first benchmark, ImageNet-C, standardizes and expands the corruption robustness topic, while showing which classifiers are preferable in…

Adversarial DefenseBenchmarkingDomain Generalization

Exploiting Frequency Spectrum of Adversarial Images for General Robustness

2023-05-15 · Chun Yang Tan, Kazuhiko Kawamoto, Hiroshi Kera

In recent years, there has been growing concern over the vulnerability of convolutional neural networks (CNNs) to image perturbations. However, achieving general robustness against different types of perturbations remain…

Data Augmentation

Label Augmentation for Neural Networks Robustness

2024-08-04 · Fatemeh Amerehi, Patrick Healy

Out-of-distribution generalization can be categorized into two types: common perturbations arising from natural variations in the real world and adversarial perturbations that are intentionally crafted to deceive neural …

Adversarial RobustnessData AugmentationOut-of-Distribution Generalization

Constant Random Perturbations Provide Adversarial Robustness with Minimal Effect on Accuracy

2021-03-15 · Bronya Roni Chernyak, Bhiksha Raj, Tamir Hazan, Joseph Keshet

This paper proposes an attack-independent (non-adversarial training) technique for improving adversarial robustness of neural network models, with minimal loss of standard accuracy. We suggest creating a neighborhood aro…

Adversarial Robustness

Defending Against Frequency-Based Attacks with Diffusion Models

2025-04-15 · Fatemeh Amerehi, Patrick Healy

Adversarial training is a common strategy for enhancing model robustness against adversarial attacks. However, it is typically tailored to the specific attack types it is trained on, limiting its ability to generalize to…

Adversarial Purification