# Improving Clean Accuracy via a Tangent-Space Perspective on Adversarial Training

arXiv: https://arxiv.org/abs/2408.14728 · HTML: https://mlsanity.com/paper/2408.14728/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 44 references that are in the map.
- First posted on arXiv 27 Aug 2024.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [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)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [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)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [Robustness May Be at Odds with Accuracy](https://mlsanity.com/paper/1805.12152/) (2018)
- [Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images](https://mlsanity.com/paper/1412.1897/) (2014)
- [Fast is better than free: Revisiting adversarial training](https://mlsanity.com/paper/2001.03994/) (2020)
- [Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment](https://mlsanity.com/paper/1907.11932/) (2019)
- [The Intrinsic Dimension of Images and Its Impact on Learning](https://mlsanity.com/paper/2104.08894/) (2021)
- [Feature Denoising for Improving Adversarial Robustness](https://mlsanity.com/paper/1812.03411/) (2018)
- [Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples](https://mlsanity.com/paper/2010.03593/) (2020)
- [Attacks Which Do Not Kill Training Make Adversarial Learning Stronger](https://mlsanity.com/paper/2002.11242/) (2020)
- [DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving](https://mlsanity.com/paper/1505.00256/) (2015)
- [Geometry-aware Instance-reweighted Adversarial Training](https://mlsanity.com/paper/2010.01736/) (2020)
- [MMA Training: Direct Input Space Margin Maximization through Adversarial Training](https://mlsanity.com/paper/1812.02637/) (2018)
- [Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systems](https://mlsanity.com/paper/1907.10456/) (2019)
- [A Boundary Tilting Persepective on the Phenomenon of Adversarial Examples](https://mlsanity.com/paper/1608.07690/) (2016)
- [CAT: Customized Adversarial Training for Improved Robustness](https://mlsanity.com/paper/2002.06789/) (2020)
- [Probabilistic Margins for Instance Reweighting in Adversarial Training](https://mlsanity.com/paper/2106.07904/) (2021)
- [Instance adaptive adversarial training: Improved accuracy tradeoffs in neural nets](https://mlsanity.com/paper/1910.08051/) (2019)
- [Dual Manifold Adversarial Robustness: Defense against Lp and non-Lp Adversarial Attacks](https://mlsanity.com/paper/2009.02470/) (2020)
- [On the Real-World Adversarial Robustness of Real-Time Semantic Segmentation Models for Autonomous Driving](https://mlsanity.com/paper/2201.01850/) (2022)
- [Understanding Adversarial Robustness Against On-manifold Adversarial Examples](https://mlsanity.com/paper/2210.00430/) (2022)

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

- [Staying on the Attractor: Supervising Neural Surrogates of 3D Turbulence Where They Leave It](https://mlsanity.com/paper/2609.32864/) (2026)

## Abstract (arXiv)

Adversarial training has proven effective in improving the robustness of deep neural networks against adversarial attacks. However, this enhanced robustness often comes at the cost of a substantial drop in accuracy on clean data. In this paper, we address this limitation by introducing Tangent Direction Guided Adversarial Training (TART), a novel method that enhances clean accuracy by exploiting the geometry of the data manifold. We argue that adversarial examples with large components in the normal direction can overly distort the decision boundary and degrade clean accuracy. TART addresses this issue by estimating the tangent direction of adversarial examples and adaptively modulating the perturbation bound based on the norm of their tangential component. To the best of our knowledge, TART is the first adversarial defense framework that explicitly incorporates the concept of tangent space and direction into adversarial training. Extensive experiments on both synthetic and benchmark datasets demonstrate that TART consistently improves clean accuracy while maintaining robustness against adversarial attacks.