自编码器检测异常可能失效，异常数据反而能被完美重建。
Autoencoders for Anomaly Detection are Unreliable
- 理论与实验证明异常数据可被自编码器完美重建
- 线性与非线性自编码器均存在外推失效问题
- 适用于安全敏感场景的异常检测研究者
自编码器常用于无监督和半监督异常检测，其核心假设是正常数据比异常数据更易重构。然而，本文揭示该假设不成立：远离正常数据分布的异常样本在实践中仍可被完美重构。通过重新分析线性自编码器的失败理论，发现其会过度外推，导致在安全关键应用中产生危险。实验覆盖表格数据与真实图像数据，验证了非线性自编码器同样存在此类问题，表明当前主流方法在异常检测中的可靠性存疑。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。