# Addressing Neural Network Robustness with Mixup and Targeted Labeling Adversarial Training

arXiv: https://arxiv.org/abs/2008.08384 · HTML: https://mlsanity.com/paper/2008.08384/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Aug 2020.

## Built on by (most cited first, 10 of 10)

- [Admix: Enhancing the Transferability of Adversarial Attacks](https://mlsanity.com/paper/2102.00436/) (2021)
- [A Systematic Review of Robustness in Deep Learning for Computer Vision: Mind the gap?](https://mlsanity.com/paper/2112.00639/) (2021)
- [A Survey of Mix-based Data Augmentation: Taxonomy, Methods, Applications, and Explainability](https://mlsanity.com/paper/2212.10888/) (2022)
- [A Survey on Mixup Augmentations and Beyond](https://mlsanity.com/paper/2409.05202/) (2024)
- [A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities](https://mlsanity.com/paper/2210.08906/) (2022)
- [Guided Interpolation for Adversarial Training](https://mlsanity.com/paper/2102.07327/) (2021)
- [Towards a Data Privacy-Predictive Performance Trade-off](https://mlsanity.com/paper/2201.05226/) (2022)
- [Robustmix: Improving Robustness by Regularizing the Frequency Bias of Deep Nets](https://mlsanity.com/paper/2304.02847/) (2023)
- [Game-Theoretic Understanding of Misclassification](https://mlsanity.com/paper/2210.03349/) (2022)
- [Exploiting Frequency Spectrum of Adversarial Images for General Robustness](https://mlsanity.com/paper/2305.08439/) (2023)

## Abstract (arXiv)

Despite their performance, Artificial Neural Networks are not reliable enough for most of industrial applications. They are sensitive to noises, rotations, blurs and adversarial examples. There is a need to build defenses that protect against a wide range of perturbations, covering the most traditional common corruptions and adversarial examples. We propose a new data augmentation strategy called M-TLAT and designed to address robustness in a broad sense. Our approach combines the Mixup augmentation and a new adversarial training algorithm called Targeted Labeling Adversarial Training (TLAT). The idea of TLAT is to interpolate the target labels of adversarial examples with the ground-truth labels. We show that M-TLAT can increase the robustness of image classifiers towards nineteen common corruptions and five adversarial attacks, without reducing the accuracy on clean samples.