# Self-supervised Adversarial Training

arXiv: https://arxiv.org/abs/1911.06470 · HTML: https://mlsanity.com/paper/1911.06470/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Nov 2019.

## Built on by (most cited first, 12 of 12)

- [Better Diffusion Models Further Improve Adversarial Training](https://mlsanity.com/paper/2302.04638/) (2023)
- [Two Coupled Rejection Metrics Can Tell Adversarial Examples Apart](https://mlsanity.com/paper/2105.14785/) (2021)
- [Out-of-Distribution Data: An Acquaintance of Adversarial Examples -- A Survey](https://mlsanity.com/paper/2404.05219/) (2024)
- [Generative Optimization Networks for Memory Efficient Data Generation](https://mlsanity.com/paper/2110.02912/) (2021)
- [Adversarial Contrastive Learning by Permuting Cluster Assignments](https://mlsanity.com/paper/2204.10314/) (2022)
- [DRAGON: Decentralized Fault Tolerance in Edge Federations](https://mlsanity.com/paper/2208.07658/) (2022)
- [UPB at SemEval-2021 Task 5: Virtual Adversarial Training for Toxic Spans Detection](https://mlsanity.com/paper/2104.08635/) (2021)
- [Language Guided Adversarial Purification](https://mlsanity.com/paper/2309.10348/) (2023)
- [Revisiting Semi-supervised Adversarial Robustness via Noise-aware Online Robust Distillation](https://mlsanity.com/paper/2409.12946/) (2024)
- [Towards Improving Robustness Against Common Corruptions in Object Detectors Using Adversarial Contrastive Learning](https://mlsanity.com/paper/2311.07928/) (2023)
- [Are Classification Robustness and Explanation Robustness Really Strongly Correlated? An Analysis Through Input Loss Landscape](https://mlsanity.com/paper/2403.06013/) (2024)
- [Adversarial Training Improves Generalization Under Distribution Shifts in Bird Sound Classification](https://mlsanity.com/paper/2507.13727/) (2025)

## Abstract (arXiv)

Recent work has demonstrated that neural networks are vulnerable to adversarial examples. To escape from the predicament, many works try to harden the model in various ways, in which adversarial training is an effective way which learns robust feature representation so as to resist adversarial attacks. Meanwhile, the self-supervised learning aims to learn robust and semantic embedding from data itself. With these views, we introduce self-supervised learning to against adversarial examples in this paper. Specifically, the self-supervised representation coupled with k-Nearest Neighbour is proposed for classification. To further strengthen the defense ability, self-supervised adversarial training is proposed, which maximizes the mutual information between the representations of original examples and the corresponding adversarial examples. Experimental results show that the self-supervised representation outperforms its supervised version in respect of robustness and self-supervised adversarial training can further improve the defense ability efficiently.