On the Adversarial Robustness of Multi-Kernel Clustering

Hao Yu, Weixuan Liang, Ke Liang, Suyuan Liu, Meng Liu, Xinwang Liu
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:73175-73196, 2025.

Abstract

Multi-kernel clustering (MKC) has emerged as a powerful method for capturing diverse data patterns, offering robust and generalized representations of data structures. However, the increasing deployment of MKC in real-world applications raises concerns about its vulnerability to adversarial perturbations. While adversarial robustness has been extensively studied in other domains, its impact on MKC remains largely unexplored. In this paper, we address the challenge of assessing the adversarial robustness of MKC methods in a black-box setting. Specifically, we propose AdvMKC, a novel reinforcement-learning-based adversarial attack framework designed to inject imperceptible perturbations into data and mislead MKC methods. AdvMKC leverages proximal policy optimization with an advantage function to overcome the instability of clustering results during optimization. Additionally, it introduces a generator-clusterer framework, where a generator produces adversarial perturbations, and a clusterer approximates MKC behavior, significantly reducing computational overhead. We provide theoretical insights into the impact of adversarial perturbations on MKC and validate these findings through experiments. Evaluations across seven datasets and eleven MKC methods (seven traditional and four robust) demonstrate AdvMKC’s effectiveness, robustness, and transferability.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-yu25m, title = {On the Adversarial Robustness of Multi-Kernel Clustering}, author = {Yu, Hao and Liang, Weixuan and Liang, Ke and Liu, Suyuan and Liu, Meng and Liu, Xinwang}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {73175--73196}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/yu25m/yu25m.pdf}, url = {https://proceedings.mlr.press/v267/yu25m.html}, abstract = {Multi-kernel clustering (MKC) has emerged as a powerful method for capturing diverse data patterns, offering robust and generalized representations of data structures. However, the increasing deployment of MKC in real-world applications raises concerns about its vulnerability to adversarial perturbations. While adversarial robustness has been extensively studied in other domains, its impact on MKC remains largely unexplored. In this paper, we address the challenge of assessing the adversarial robustness of MKC methods in a black-box setting. Specifically, we propose AdvMKC, a novel reinforcement-learning-based adversarial attack framework designed to inject imperceptible perturbations into data and mislead MKC methods. AdvMKC leverages proximal policy optimization with an advantage function to overcome the instability of clustering results during optimization. Additionally, it introduces a generator-clusterer framework, where a generator produces adversarial perturbations, and a clusterer approximates MKC behavior, significantly reducing computational overhead. We provide theoretical insights into the impact of adversarial perturbations on MKC and validate these findings through experiments. Evaluations across seven datasets and eleven MKC methods (seven traditional and four robust) demonstrate AdvMKC’s effectiveness, robustness, and transferability.} }
Endnote
%0 Conference Paper %T On the Adversarial Robustness of Multi-Kernel Clustering %A Hao Yu %A Weixuan Liang %A Ke Liang %A Suyuan Liu %A Meng Liu %A Xinwang Liu %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-yu25m %I PMLR %P 73175--73196 %U https://proceedings.mlr.press/v267/yu25m.html %V 267 %X Multi-kernel clustering (MKC) has emerged as a powerful method for capturing diverse data patterns, offering robust and generalized representations of data structures. However, the increasing deployment of MKC in real-world applications raises concerns about its vulnerability to adversarial perturbations. While adversarial robustness has been extensively studied in other domains, its impact on MKC remains largely unexplored. In this paper, we address the challenge of assessing the adversarial robustness of MKC methods in a black-box setting. Specifically, we propose AdvMKC, a novel reinforcement-learning-based adversarial attack framework designed to inject imperceptible perturbations into data and mislead MKC methods. AdvMKC leverages proximal policy optimization with an advantage function to overcome the instability of clustering results during optimization. Additionally, it introduces a generator-clusterer framework, where a generator produces adversarial perturbations, and a clusterer approximates MKC behavior, significantly reducing computational overhead. We provide theoretical insights into the impact of adversarial perturbations on MKC and validate these findings through experiments. Evaluations across seven datasets and eleven MKC methods (seven traditional and four robust) demonstrate AdvMKC’s effectiveness, robustness, and transferability.
APA
Yu, H., Liang, W., Liang, K., Liu, S., Liu, M. & Liu, X.. (2025). On the Adversarial Robustness of Multi-Kernel Clustering. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:73175-73196 Available from https://proceedings.mlr.press/v267/yu25m.html.

Related Material