# Decoder-free Robustness Disentanglement without (Additional) Supervision

arXiv: https://arxiv.org/abs/2007.01356 · HTML: https://mlsanity.com/paper/2007.01356/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jul 2020.

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

- [Balance, Imbalance, and Rebalance: Understanding Robust Overfitting from a Minimax Game Perspective](https://mlsanity.com/paper/2310.19360/) (2023)

## Abstract (arXiv)

Adversarial Training (AT) is proposed to alleviate the adversarial vulnerability of machine learning models by extracting only robust features from the input, which, however, inevitably leads to severe accuracy reduction as it discards the non-robust yet useful features. This motivates us to preserve both robust and non-robust features and separate them with disentangled representation learning. Our proposed Adversarial Asymmetric Training (AAT) algorithm can reliably disentangle robust and non-robust representations without additional supervision on robustness. Empirical results show our method does not only successfully preserve accuracy by combining two representations, but also achieve much better disentanglement than previous work.