Autoencoder (AE) is a neural network (NN) architecture that is trained to reconstruct an input at its output. By measuring the reconstruction errors of new input samples, AE can detect anomalous samples deviated from the trained data distribution. The key to success is to achieve high-fidelity reconstruction (HFR) while restricting AE's capability of generalization beyond training data, which should be balanced commonly via iterative re-training. Alternatively, we propose a novel framework of AE-based anomaly detection, coined HFR-AE, by projecting new inputs into a subspace wherein the trained AE achieves HFR, thereby increasing the gap between normal and anomalous sample reconstruction errors. Simulation results corroborate that HFR-AE improves the area under receiver operating characteristic curve (AUROC) under different AE architectures and settings by up to 13.4% compared to Vanilla AE-based anomaly detection.

翻译：自编码器（AE）是一种神经网络（NN）架构，旨在其输出端重建输入。通过测量新输入样本的重建误差，AE能检测偏离训练数据分布的异常样本。其成功关键在于实现高保真重建（HFR）的同时限制AE对训练数据之外数据的泛化能力，通常需通过迭代训练来平衡两者。为此，我们提出一种新型AE异常检测框架HFR-AE，通过将新输入投影至训练后AE可实现HFR的子空间中，从而增大正常样本与异常样本重建误差之间的差距。仿真结果证实，相较于原始AE异常检测方法，HFR-AE在不同AE架构与设置下将受试者工作特征曲线下面积（AUROC）提升最高达13.4%。