Unsupervised anomaly-based intrusion detection requires models that can generalize to attack patterns not observed during training. This work presents the first large-scale evaluation of hybrid quantum-classical (HQC) autoencoders for this task. We construct a unified experimental framework that iterates over key quantum design choices, including quantum-layer placement, measurement approach, variational and non-variational formulations, and latent-space regularization. Experiments across three benchmark NIDS datasets show that HQC autoencoders can match or exceed classical performance in their best configurations, although they exhibit higher sensitivity to architectural decisions. Under zero-day evaluation, well-configured HQC models provide stronger and more stable generalization than classical and supervised baselines. Simulated gate-noise experiments reveal early performance degradation, indicating the need for noise-aware HQC designs. These results provide the first data-driven characterization of HQC autoencoder behavior for network intrusion detection and outline key factors that govern their practical viability. All experiment code and configurations are available at https://github.com/arasyi/hqcae-network-intrusion-detection.

翻译：无监督基于异常的入侵检测需要模型能够泛化至训练期间未观测到的攻击模式。本研究首次针对该任务对混合量子-经典（HQC）自编码器进行了大规模评估。我们构建了一个统一的实验框架，迭代探索了关键量子设计选项，包括量子层放置位置、测量方法、变分与非变分架构，以及潜在空间正则化。在三个基准网络入侵检测系统数据集上的实验表明，HQC自编码器在最优配置下能够达到或超越经典模型的性能，尽管其对架构决策表现出更高的敏感性。在零日攻击评估场景下，配置良好的HQC模型相比经典模型与有监督基线方法展现出更强且更稳定的泛化能力。模拟门噪声实验揭示了早期性能退化现象，表明需要开发噪声感知的HQC设计。这些结果为网络入侵检测中HQC自编码器的行为提供了首个数据驱动的特征描述，并阐明了影响其实际可行性的关键因素。所有实验代码与配置均已公开：https://github.com/arasyi/hqcae-network-intrusion-detection。