# Characterizing Model Robustness via Natural Input Gradients

arXiv: https://arxiv.org/abs/2409.20139 · HTML: https://mlsanity.com/paper/2409.20139/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 62 references that are in the map.
- First posted on arXiv 30 Sep 2024.

## Builds on (most cited first, 30 of 50)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks](https://mlsanity.com/paper/2003.01690/) (2020)
- [Certified Adversarial Robustness via Randomized Smoothing](https://mlsanity.com/paper/1902.02918/) (2019)
- [Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples](https://mlsanity.com/paper/1802.00420/) (2018)
- [Averaging Weights Leads to Wider Optima and Better Generalization](https://mlsanity.com/paper/1803.05407/) (2018)
- [Adversarial Machine Learning at Scale](https://mlsanity.com/paper/1611.01236/) (2016)
- [Ensemble Adversarial Training: Attacks and Defenses](https://mlsanity.com/paper/1705.07204/) (2017)
- [AutoAugment: Learning Augmentation Policies from Data](https://mlsanity.com/paper/1805.09501/) (2018)
- [Fast is better than free: Revisiting adversarial training](https://mlsanity.com/paper/2001.03994/) (2020)
- [RobustBench: a standardized adversarial robustness benchmark](https://mlsanity.com/paper/2010.09670/) (2020)
- [Improving Transferability of Adversarial Examples with Input Diversity](https://mlsanity.com/paper/1803.06978/) (2018)
- [Provable defenses against adversarial examples via the convex outer adversarial polytope](https://mlsanity.com/paper/1711.00851/) (2017)
- [Countering Adversarial Images using Input Transformations](https://mlsanity.com/paper/1711.00117/) (2017)
- [On Evaluating Adversarial Robustness](https://mlsanity.com/paper/1902.06705/) (2019)
- [Mitigating Adversarial Effects Through Randomization](https://mlsanity.com/paper/1711.01991/) (2017)
- [Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser](https://mlsanity.com/paper/1712.02976/) (2017)
- [Do Adversarially Robust ImageNet Models Transfer Better?](https://mlsanity.com/paper/2007.08489/) (2020)
- [Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples](https://mlsanity.com/paper/2010.03593/) (2020)
- [Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients](https://mlsanity.com/paper/1711.09404/) (2017)

## Built on by (most cited first, 6 of 6)

- [The Linear Centroids Hypothesis: Features as Directions Learned by Local Experts](https://mlsanity.com/paper/2604.11962/) (2026)
- [Solving adversarial examples requires solving exponential misalignment](https://mlsanity.com/paper/2603.03507/) (2026)
- [Secure Diagnostics: Adversarial Robustness Meets Clinical Interpretability](https://mlsanity.com/paper/2504.05483/) (2025)
- [Dynamic Parameter Optimization for Highly Transferable Transformation-Based Attacks](https://mlsanity.com/paper/2511.11993/) (2025)
- [DeepDefense: Robust Learning via Layer-Wise Gradient-Feature Alignment](https://mlsanity.com/paper/2511.13749/) (2025)
- [Adversarial Frontiers: Minimum-Norm Attack Ensembles for Robustness Evaluation](https://mlsanity.com/paper/2607.19855/) (2026)

## Abstract (arXiv)

Adversarially robust models are locally smooth around each data sample so that small perturbations cannot drastically change model outputs. In modern systems, such smoothness is usually obtained via Adversarial Training, which explicitly enforces models to perform well on perturbed examples. In this work, we show the surprising effectiveness of instead regularizing the gradient with respect to model inputs on natural examples only. Penalizing input Gradient Norm is commonly believed to be a much inferior approach. Our analyses identify that the performance of Gradient Norm regularization critically depends on the smoothness of activation functions, and are in fact extremely effective on modern vision transformers that adopt smooth activations over piecewise linear ones (eg, ReLU), contrary to prior belief. On ImageNet-1k, Gradient Norm training achieves > 90% the performance of state-of-the-art PGD-3 Adversarial Training} (52% vs.~56%), while using only 60% computation cost of the state-of-the-art without complex adversarial optimization. Our analyses also highlight the relationship between model robustness and properties of natural input gradients, such as asymmetric sample and channel statistics. Surprisingly, we find model robustness can be significantly improved by simply regularizing its gradients to concentrate on image edges without explicit conditioning on the gradient norm.