Diffusion models have been recently used for anomaly detection (AD) in images. In this paper we investigate whether they can also be leveraged for AD on multivariate time series (MTS). We test two diffusion-based models and compare them to several strong neural baselines. We also extend the PA%K protocol, by computing a ROCK-AUC metric, which is agnostic to both the detection threshold and the ratio K of correctly detected points. Our models outperform the baselines on synthetic datasets and are competitive on real-world datasets, illustrating the potential of diffusion-based methods for AD in multivariate time series.

翻译：扩散模型最近已被用于图像异常检测（AD）。本文研究了能否将其应用于多变量时间序列（MTS）的异常检测。我们测试了两种基于扩散的模型，并将其与多个强神经网络基线进行了比较。我们还通过计算ROC-AUC指标扩展了PA%K协议，该指标既不受检测阈值影响，也与正确检测点的比例K无关。我们的模型在合成数据集上优于基线方法，并在真实数据集上表现出竞争力，这展示了基于扩散的方法在多变量时间序列异常检测中的潜力。