用于异常检测的自编码器不可靠
Autoencoders for Anomaly Detection are Unreliable
AI总结：
本文证明自编码器在异常检测中基于重建损失的假设不成立，异常可被完美重建，线性与非线性自编码器均存在风险，对安全关键应用构成威胁。
摘要：
自编码器经常用于异常检测，无论是在无监督还是半监督设置下。它们依赖于这样一个假设：当使用重建损失进行训练时，它们将能够比异常数据更准确地重建正常数据。一些近期工作提出这一假设可能并非总是成立，但很少有工作从理论上研究该假设的有效性。在这项工作中，我们表明这一假设确实不成立，并说明远离正常数据的异常在实践中可以被完美重建。我们重新审视线性自编码器在异常检测中失败的理论，通过展示它们如何完美重建超出边界的数据，或进行不良的外推，并指出这在安全关键应用中可能带来的危险。我们通过表格数据和真实世界图像数据上的实验将这一现象与非线性自编码器联系起来，这两个领域是自编码器用于异常检测的主要应用领域。
英文摘要：
Autoencoders are frequently used for anomaly detection, both in the unsupervised and semi-supervised settings. They rely on the assumption that when trained using the reconstruction loss, they will be able to reconstruct normal data more accurately than anomalous data. Some recent works have posited that this assumption may not always hold, but little has been done to study the validity of the assumption in theory. In this work we show that this assumption indeed does not hold, and illustrate that anomalies, lying far away from normal data, can be perfectly reconstructed in practice. We revisit the theory of failure of linear autoencoders for anomaly detection by showing how they can perfectly reconstruct out of bounds, or extrapolate undesirably, and note how this can be dangerous in safety critical applications. We connect this to non-linear autoencoders through experiments on both tabular data and real-world image data, the two primary application areas of autoencoders for anomaly detection.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
