# Rethinking Clustering for Robustness

arXiv: https://arxiv.org/abs/2006.07682 · HTML: https://mlsanity.com/paper/2006.07682/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jun 2020.

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

- [SpikeFit: Towards Optimal Deployment of Spiking Networks on Neuromorphic Hardware](https://mlsanity.com/paper/2510.15542/) (2025)

## Abstract (arXiv)

This paper studies how encouraging semantically-aligned features during deep neural network training can increase network robustness. Recent works observed that Adversarial Training leads to robust models, whose learnt features appear to correlate with human perception. Inspired by this connection from robustness to semantics, we study the complementary connection: from semantics to robustness. To do so, we provide a robustness certificate for distance-based classification models (clustering-based classifiers). Moreover, we show that this certificate is tight, and we leverage it to propose ClusTR (Clustering Training for Robustness), a clustering-based and adversary-free training framework to learn robust models. Interestingly, textitClusTR outperforms adversarially-trained networks by up to 4% under strong PGD attacks.