# Provably Robust Metric Learning

arXiv: https://arxiv.org/abs/2006.07024 · HTML: https://mlsanity.com/paper/2006.07024/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jun 2020.

## Built on by (most cited first, 3 of 3)

- [Efficient LLM Moderation with Multi-Layer Latent Prototypes](https://mlsanity.com/paper/2502.16174/) (2025)
- [Conditioned Activation Transport for T2I Safety Steering](https://mlsanity.com/paper/2603.03163/) (2026)
- [Regressing Relative Fine-Grained Change for Sub-Groups in Unreliable Heterogeneous Data Through Deep Multi-Task Metric Learning](https://mlsanity.com/paper/2208.05800/) (2022)

## Abstract (arXiv)

Metric learning is an important family of algorithms for classification and similarity search, but the robustness of learned metrics against small adversarial perturbations is less studied. In this paper, we show that existing metric learning algorithms, which focus on boosting the clean accuracy, can result in metrics that are less robust than the Euclidean distance. To overcome this problem, we propose a novel metric learning algorithm to find a Mahalanobis distance that is robust against adversarial perturbations, and the robustness of the resulting model is certifiable. Experimental results show that the proposed metric learning algorithm improves both certified robust errors and empirical robust errors (errors under adversarial attacks). Furthermore, unlike neural network defenses which usually encounter a trade-off between clean and robust errors, our method does not sacrifice clean errors compared with previous metric learning methods. Our code is available at https://github.com/wangwllu/provably_robust_metric_learning.