Feature-level analysis and adversarial transfer in rotationally equivariant quantum machine learning

Quantum Physics [Submitted on 16 Apr 2026] Feature-level analysis and adversarial transfer in rotationally equivariant quantum machine learning Maureen Krumtünger, Martin Sevior, Muhammad Usman Group-equivariant quantum models are designed to exploit symmetry and can improve trainability, but it remains unclear how symmetry constraints shape their adversarial robustness. We study this question through a feature-level analysis of equivariant quantum models in a transfer-attack setting. Under equivariance with an invariant readout, predictions depend only on the group-twirled input, which identifies the symmetry-invariant information accessible to the model together with a complementary uninformative subspace. Specializing this framework to a rotationally equivariant quantum model, we derive an explicit characterization of the accessible information in terms of rotation-invariant image statistics distributed across distinct symmetry sectors. Using targeted input transformations, we determine which of these statistics are actually relied upon for classification across several datasets. We find that equivariance alone does not guarantee transfer robustness: even within the restricted invariant feature space, the model can rely on brittle statistics, particularly ring-averaged intensities in the rotationally equivariant model, that remain vulnerable to classical transfer attacks. Guided by this analysis, we show that suppressing the symmetry sector associated with the brittle feature substantially improves robustness. These results establish a systematic mechanism to exploit symmetry-dependent features for adversarial robustness in future quantum machine learning models. Subjects: Quantum Physics (quant-ph) Cite as: arXiv:2604.15552 [quant-ph]   (or arXiv:2604.15552v1 [quant-ph] for this version)   https://doi.org/10.48550/arXiv.2604.15552 Focus to learn more Submission history From: Maureen Krumtünger [view email] [v1] Thu, 16 Apr 2026 22:06:00 UTC (772 KB) Access Paper: HTML (experimental) view license Current browse context: quant-ph < prev   |   next > new | recent | 2026-04 References & Citations INSPIRE HEP NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)