# Detection of Adversarial Attacks and Characterization of Adversarial Subspace

arXiv: https://arxiv.org/abs/1910.12084 · HTML: https://mlsanity.com/paper/1910.12084/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Oct 2019.

## Built on by (most cited first, 7 of 7)

- [Adversarial Attacks and Defenses in Machine Learning-Powered Networks: A Contemporary Survey](https://mlsanity.com/paper/2303.06302/) (2023)
- [Multi-Discriminator Sobolev Defense-GAN Against Adversarial Attacks for End-to-End Speech Systems](https://mlsanity.com/paper/2103.08086/) (2021)
- [Towards Robust Speech-to-Text Adversarial Attack](https://mlsanity.com/paper/2103.08095/) (2021)
- [Bi-Discriminator Class-Conditional Tabular GAN](https://mlsanity.com/paper/2111.06549/) (2021)
- [Diffusion Models are Robust Pretrainers](https://mlsanity.com/paper/2511.02793/) (2025)
- [Adversarial Robustness of Deep Reinforcement Learning based Dynamic Recommender Systems](https://mlsanity.com/paper/2112.00973/) (2021)
- [RSD-GAN: Regularized Sobolev Defense GAN Against Speech-to-Text Adversarial Attacks](https://mlsanity.com/paper/2207.06858/) (2022)

## Abstract (arXiv)

Adversarial attacks have always been a serious threat for any data-driven model. In this paper, we explore subspaces of adversarial examples in unitary vector domain, and we propose a novel detector for defending our models trained for environmental sound classification. We measure chordal distance between legitimate and malicious representation of sounds in unitary space of generalized Schur decomposition and show that their manifolds lie far from each other. Our front-end detector is a regularized logistic regression which discriminates eigenvalues of legitimate and adversarial spectrograms. The experimental results on three benchmarking datasets of environmental sounds represented by spectrograms reveal high detection rate of the proposed detector for eight types of adversarial attacks and outperforms other detection approaches.