# Backdoor Attacks against Hybrid Classical-Quantum Neural Networks

arXiv: https://arxiv.org/abs/2407.16273 · HTML: https://mlsanity.com/paper/2407.16273/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jul 2024.

## Built on by (most cited first, 5 of 5)

- [State Backdoor: Towards Stealthy Real-world Poisoning Attack on Vision-Language-Action Model in State Space](https://mlsanity.com/paper/2601.04266/) (2026)
- [BadRefSR: Backdoor Attacks Against Reference-based Image Super Resolution](https://mlsanity.com/paper/2502.20943/) (2025)
- [DSAS: A Universal Plug-and-Play Framework for Attention Optimization in Multi-Document Question Answering](https://mlsanity.com/paper/2510.12251/) (2025)
- [CBV: Clean-label Backdoor Attacks on Vision Language Models via Diffusion Models](https://mlsanity.com/paper/2605.02202/) (2026)
- [Geometry-Aware Backdoor Attacks: Leveraging Curvature in Hyperbolic Embeddings](https://mlsanity.com/paper/2510.06397/) (2025)

## Abstract (arXiv)

Hybrid Quantum Neural Networks (HQNNs) represent a promising advancement in Quantum Machine Learning (QML), yet their security has been rarely explored. In this paper, we present the first systematic study of backdoor attacks on HQNNs. We begin by proposing an attack framework and providing a theoretical analysis of the generalization bounds and minimum perturbation requirements for backdoor attacks on HQNNs. Next, we employ two classic backdoor attack methods on HQNNs and Convolutional Neural Networks (CNNs) to further investigate the robustness of HQNNs. Our experimental results demonstrate that HQNNs are more robust than CNNs, requiring more significant image modifications for successful attacks. Additionally, we introduce the Qcolor backdoor, which utilizes color shifts as triggers and employs the Non-dominated Sorting Genetic Algorithm II (NSGA-II) to optimize hyperparameters. Through extensive experiments, we demonstrate the effectiveness, stealthiness, and robustness of the Qcolor backdoor.