# Enhancing Robust Representation in Adversarial Training: Alignment and Exclusion Criteria

arXiv: https://arxiv.org/abs/2310.03358 · HTML: https://mlsanity.com/paper/2310.03358/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 44 of its 61 references that are in the map.
- First posted on arXiv 5 Oct 2023.

## Builds on (most cited first, 30 of 44)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [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)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (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)
- [Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser](https://mlsanity.com/paper/1712.02976/) (2017)
- [Adversarial Examples for Semantic Segmentation and Object Detection](https://mlsanity.com/paper/1703.08603/) (2017)
- [Attacks Which Do Not Kill Training Make Adversarial Learning Stronger](https://mlsanity.com/paper/2002.11242/) (2020)
- [Adversarial Logit Pairing](https://mlsanity.com/paper/1803.06373/) (2018)
- [MMA Training: Direct Input Space Margin Maximization through Adversarial Training](https://mlsanity.com/paper/1812.02637/) (2018)
- [Robust Pre-Training by Adversarial Contrastive Learning](https://mlsanity.com/paper/2010.13337/) (2020)
- [Adversarial Self-Supervised Contrastive Learning](https://mlsanity.com/paper/2006.07589/) (2020)
- [Self-Adaptive Training: beyond Empirical Risk Minimization](https://mlsanity.com/paper/2002.10319/) (2020)
- [Boosting Contrastive Self-Supervised Learning with False Negative Cancellation](https://mlsanity.com/paper/2011.11765/) (2020)
- [Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?](https://mlsanity.com/paper/2104.09425/) (2021)
- [When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?](https://mlsanity.com/paper/2111.01124/) (2021)
- [Improving Adversarial Robustness via Channel-wise Activation Suppressing](https://mlsanity.com/paper/2103.08307/) (2021)
- [Bad Characters: Imperceptible NLP Attacks](https://mlsanity.com/paper/2106.09898/) (2021)
- [Exploring Memorization in Adversarial Training](https://mlsanity.com/paper/2106.01606/) (2021)
- [Evaluating the Robustness of Semantic Segmentation for Autonomous Driving against Real-World Adversarial Patch Attacks](https://mlsanity.com/paper/2108.06179/) (2021)
- [Enhancing Adversarial Defense by k-Winners-Take-All](https://mlsanity.com/paper/1905.10510/) (2019)
- [Efficient and Effective Augmentation Strategy for Adversarial Training](https://mlsanity.com/paper/2210.15318/) (2022)

## Abstract (arXiv)

Deep neural networks are vulnerable to adversarial noise. Adversarial Training (AT) has been demonstrated to be the most effective defense strategy to protect neural networks from being fooled. However, we find AT omits to learning robust features, resulting in poor performance of adversarial robustness. To address this issue, we highlight two criteria of robust representation: (1) Exclusion: the feature of examples keeps away from that of other classes; (2) Alignment: the feature of natural and corresponding adversarial examples is close to each other. These motivate us to propose a generic framework of AT to gain robust representation, by the asymmetric negative contrast and reverse attention. Specifically, we design an asymmetric negative contrast based on predicted probabilities, to push away examples of different classes in the feature space. Moreover, we propose to weight feature by parameters of the linear classifier as the reverse attention, to obtain class-aware feature and pull close the feature of the same class. Empirical evaluations on three benchmark datasets show our methods greatly advance the robustness of AT and achieve state-of-the-art performance.