# Adversarial training may be a double-edged sword

arXiv: https://arxiv.org/abs/2107.11671 · HTML: https://mlsanity.com/paper/2107.11671/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 19 references that are in the map.
- First posted on arXiv 24 Jul 2021.

## Builds on (most cited first, 17 of 17)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [Fast is better than free: Revisiting adversarial training](https://mlsanity.com/paper/2001.03994/) (2020)
- [ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models](https://mlsanity.com/paper/1708.03999/) (2017)
- [Adversarial Training for Free!](https://mlsanity.com/paper/1904.12843/) (2019)
- [Black-box Adversarial Attacks with Limited Queries and Information](https://mlsanity.com/paper/1804.08598/) (2018)
- [Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models](https://mlsanity.com/paper/1712.04248/) (2017)
- [HopSkipJumpAttack: A Query-Efficient Decision-Based Attack](https://mlsanity.com/paper/1904.02144/) (2019)
- [Robustness via curvature regularization, and vice versa](https://mlsanity.com/paper/1811.09716/) (2018)
- [Adversarial Robustness through Local Linearization](https://mlsanity.com/paper/1907.02610/) (2019)
- [Sign-OPT: A Query-Efficient Hard-label Adversarial Attack](https://mlsanity.com/paper/1909.10773/) (2019)
- [GeoDA: a geometric framework for black-box adversarial attacks](https://mlsanity.com/paper/2003.06468/) (2020)
- [Simple Black-Box Adversarial Perturbations for Deep Networks](https://mlsanity.com/paper/1612.06299/) (2016)
- [A geometry-inspired decision-based attack](https://mlsanity.com/paper/1903.10826/) (2019)

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

- [Robustness and invariance properties of image classifiers](https://mlsanity.com/paper/2209.02408/) (2022)

## Abstract (arXiv)

Adversarial training has been shown as an effective approach to improve the robustness of image classifiers against white-box attacks. However, its effectiveness against black-box attacks is more nuanced. In this work, we demonstrate that some geometric consequences of adversarial training on the decision boundary of deep networks give an edge to certain types of black-box attacks. In particular, we define a metric called robustness gain to show that while adversarial training is an effective method to dramatically improve the robustness in white-box scenarios, it may not provide such a good robustness gain against the more realistic decision-based black-box attacks. Moreover, we show that even the minimal perturbation white-box attacks can converge faster against adversarially-trained neural networks compared to the regular ones.