# Are Adversarial Robustness and Common Perturbation Robustness Independent Attributes ?

arXiv: https://arxiv.org/abs/1909.02436 · HTML: https://mlsanity.com/paper/1909.02436/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Sep 2019.

## Built on by (most cited first, 25 of 25)

- [Understanding Robustness of Transformers for Image Classification](https://mlsanity.com/paper/2103.14586/) (2021)
- [A Systematic Review of Robustness in Deep Learning for Computer Vision: Mind the gap?](https://mlsanity.com/paper/2112.00639/) (2021)
- [Multi-Objective Hyperparameter Optimization in Machine Learning -- An Overview](https://mlsanity.com/paper/2206.07438/) (2022)
- [Towards Robust Video Object Segmentation with Adaptive Object Calibration](https://mlsanity.com/paper/2207.00887/) (2022)
- [Emergence of Shape Bias in Convolutional Neural Networks through Activation Sparsity](https://mlsanity.com/paper/2310.18894/) (2023)
- [Machine Learning Robustness: A Primer](https://mlsanity.com/paper/2404.00897/) (2024)
- [SegSTRONG-C: Segmenting Surgical Tools Robustly On Non-adversarial Generated Corruptions -- An EndoVis'24 Challenge](https://mlsanity.com/paper/2407.11906/) (2024)
- [Onboard Satellite Image Classification for Earth Observation: A Comparative Study of ViT Models](https://mlsanity.com/paper/2409.03901/) (2024)
- [Using Synthetic Corruptions to Measure Robustness to Natural Distribution Shifts](https://mlsanity.com/paper/2107.12052/) (2021)
- [Joint rotational invariance and adversarial training of a dual-stream Transformer yields state of the art Brain-Score for Area V4](https://mlsanity.com/paper/2203.06649/) (2022)
- [RobustCLEVR: A Benchmark and Framework for Evaluating Robustness in Object-centric Learning](https://mlsanity.com/paper/2308.14899/) (2023)
- [Real World Robustness from Systematic Noise](https://mlsanity.com/paper/2109.00864/) (2021)
- [AIREPAIR: A Repair Platform for Neural Networks](https://mlsanity.com/paper/2211.15387/) (2022)
- [Natural Perturbed Training for General Robustness of Neural Network Classifiers](https://mlsanity.com/paper/2103.11372/) (2021)
- [Game-Theoretic Understanding of Misclassification](https://mlsanity.com/paper/2210.03349/) (2022)
- [Causality-Driven Audits of Model Robustness](https://mlsanity.com/paper/2410.23494/) (2024)
- [Balancing Robustness and Sensitivity using Feature Contrastive Learning](https://mlsanity.com/paper/2105.09394/) (2021)
- [Using the Overlapping Score to Improve Corruption Benchmarks](https://mlsanity.com/paper/2105.12357/) (2021)
- [Interpreting Global Perturbation Robustness of Image Models using Axiomatic Spectral Importance Decomposition](https://mlsanity.com/paper/2408.01139/) (2024)
- [Label Augmentation for Neural Networks Robustness](https://mlsanity.com/paper/2408.01977/) (2024)
- [Comparative Study on Noise-Augmented Training and its Effect on Adversarial Robustness in ASR Systems](https://mlsanity.com/paper/2409.01813/) (2024)
- [Robust Deep Learning Models Against Semantic-Preserving Adversarial Attack](https://mlsanity.com/paper/2304.03955/) (2023)
- [Exploiting Frequency Spectrum of Adversarial Images for General Robustness](https://mlsanity.com/paper/2305.08439/) (2023)
- [A Causal Framework for Aligning Image Quality Metrics and Deep Neural Network Robustness](https://mlsanity.com/paper/2503.02797/) (2025)
- [Instant Video Models: Universal Adapters for Stabilizing Image-Based Networks](https://mlsanity.com/paper/2512.03014/) (2025)

## Abstract (arXiv)

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.