# Improving Adversarial Robustness by Enforcing Local and Global Compactness

arXiv: https://arxiv.org/abs/2007.05123 · HTML: https://mlsanity.com/paper/2007.05123/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jul 2020.

## Built on by (most cited first, 11 of 11)

- [Advances in adversarial attacks and defenses in computer vision: A survey](https://mlsanity.com/paper/2108.00401/) (2021)
- [Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation](https://mlsanity.com/paper/2410.15618/) (2024)
- [Fantastic Targets for Concept Erasure in Diffusion Models and Where To Find Them](https://mlsanity.com/paper/2501.18950/) (2025)
- [A Unified Wasserstein Distributional Robustness Framework for Adversarial Training](https://mlsanity.com/paper/2202.13437/) (2022)
- [Improving Robustness by Enhancing Weak Subnets](https://mlsanity.com/paper/2201.12765/) (2022)
- [Learning Diverse-Structured Networks for Adversarial Robustness](https://mlsanity.com/paper/2102.01886/) (2021)
- [Global-Local Regularization Via Distributional Robustness](https://mlsanity.com/paper/2203.00553/) (2022)
- [It Is All About Data: A Survey on the Effects of Data on Adversarial Robustness](https://mlsanity.com/paper/2303.09767/) (2023)
- [Understanding and Achieving Efficient Robustness with Adversarial Supervised Contrastive Learning](https://mlsanity.com/paper/2101.10027/) (2021)
- [Generating Adversarial Examples with Task Oriented Multi-Objective Optimization](https://mlsanity.com/paper/2304.13229/) (2023)
- [Generalization Bounds for Robust Contrastive Learning: From Theory to Practice](https://mlsanity.com/paper/2311.09671/) (2023)

## Abstract (arXiv)

The fact that deep neural networks are susceptible to crafted perturbations severely impacts the use of deep learning in certain domains of application. Among many developed defense models against such attacks, adversarial training emerges as the most successful method that consistently resists a wide range of attacks. In this work, based on an observation from a previous study that the representations of a clean data example and its adversarial examples become more divergent in higher layers of a deep neural net, we propose the Adversary Divergence Reduction Network which enforces local/global compactness and the clustering assumption over an intermediate layer of a deep neural network. We conduct comprehensive experiments to understand the isolating behavior of each component (i.e., local/global compactness and the clustering assumption) and compare our proposed model with state-of-the-art adversarial training methods. The experimental results demonstrate that augmenting adversarial training with our proposed components can further improve the robustness of the network, leading to higher unperturbed and adversarial predictive performances.