# Adversarial Robustness on Image Classification with $k$-means

Source: [Adversarial Robustness on Image Classification with $k$-means](<https://www.sota2.com/research/paper/68fa72221e209131cea54b3c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:30:07.706Z

Authors: Rollin Omari, Junae Kim, Paul Montague

Published: 2023-12-15T04:51:43.000Z

## Abstract

In this paper we explore the challenges and strategies for enhancing the robustness of $k$-means clustering algorithms against adversarial manipulations. We evaluate the vulnerability of clustering algorithms to adversarial attacks, emphasising the associated security risks. Our study investigates the impact of incremental attack strength on training, introduces the concept of transferability between supervised and unsupervised models, and highlights the sensitivity of unsupervised models to sample distributions. We additionally introduce and evaluate an adversarial training method that improves testing performance in adversarial scenarios, and we highlight the importance of various parameters in the proposed training method, such as continuous learning, centroid initialisation, and adversarial step-count.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2312.09533>)

[PDF](<https://arxiv.org/pdf/2312.09533.pdf>)