# A Hierarchical Assessment of Adversarial Severity

arXiv: https://arxiv.org/abs/2108.11785 · HTML: https://mlsanity.com/paper/2108.11785/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 45 references that are in the map.
- First posted on arXiv 26 Aug 2021.

## Builds on (most cited first, 28 of 28)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [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)
- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Theoretically Principled Trade-off between Robustness and Accuracy](https://mlsanity.com/paper/1901.08573/) (2019)
- [Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks](https://mlsanity.com/paper/2003.01690/) (2020)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [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)
- [Practical Black-Box Attacks against Machine Learning](https://mlsanity.com/paper/1602.02697/) (2016)
- [On the Convergence of Adam and Beyond](https://mlsanity.com/paper/1904.09237/) (2019)
- [Adversarial Training for Free!](https://mlsanity.com/paper/1904.12843/) (2019)
- [Meta-Learning for Semi-Supervised Few-Shot Classification](https://mlsanity.com/paper/1803.00676/) (2018)
- [Video Object Segmentation using Space-Time Memory Networks](https://mlsanity.com/paper/1904.00607/) (2019)
- [Certified Defenses against Adversarial Examples](https://mlsanity.com/paper/1801.09344/) (2018)
- [On The Power of Curriculum Learning in Training Deep Networks](https://mlsanity.com/paper/1904.03626/) (2019)
- [Automated Curriculum Learning for Neural Networks](https://mlsanity.com/paper/1704.03003/) (2017)
- [Latent Embeddings for Zero-shot Classification](https://mlsanity.com/paper/1603.08895/) (2016)
- [Making Better Mistakes: Leveraging Class Hierarchies with Deep Networks](https://mlsanity.com/paper/1912.09393/) (2019)
- [Curriculum DeepSDF](https://mlsanity.com/paper/2003.08593/) (2020)
- [Do Convolutional Neural Networks Learn Class Hierarchy?](https://mlsanity.com/paper/1710.06501/) (2017)
- [Network of Experts for Large-Scale Image Categorization](https://mlsanity.com/paper/1604.06119/) (2016)
- [Bilateral Adversarial Training: Towards Fast Training of More Robust Models Against Adversarial Attacks](https://mlsanity.com/paper/1811.10716/) (2018)
- [Hierarchy-based Image Embeddings for Semantic Image Retrieval](https://mlsanity.com/paper/1809.09924/) (2018)
- [Theory of Curriculum Learning, with Convex Loss Functions](https://mlsanity.com/paper/1812.03472/) (2018)
- [HD-CNN: Hierarchical Deep Convolutional Neural Network for Large Scale Visual Recognition](https://mlsanity.com/paper/1410.0736/) (2014)

## Built on by (most cited first, 1 of 1)

- [Adversarial Counterfactual Visual Explanations](https://mlsanity.com/paper/2303.09962/) (2023)

## Abstract (arXiv)

Adversarial Robustness is a growing field that evidences the brittleness of neural networks. Although the literature on adversarial robustness is vast, a dimension is missing in these studies: assessing how severe the mistakes are. We call this notion "Adversarial Severity" since it quantifies the downstream impact of adversarial corruptions by computing the semantic error between the misclassification and the proper label. We propose to study the effects of adversarial noise by measuring the Robustness and Severity into a large-scale dataset: iNaturalist-H. Our contributions are: (i) we introduce novel Hierarchical Attacks that harness the rich structured space of labels to create adversarial examples. (ii) These attacks allow us to benchmark the Adversarial Robustness and Severity of classification models. (iii) We enhance the traditional adversarial training with a simple yet effective Hierarchical Curriculum Training to learn these nodes gradually within the hierarchical tree. We perform extensive experiments showing that hierarchical defenses allow deep models to boost the adversarial Robustness by 1.85% and reduce the severity of all attacks by 0.17, on average.