Anomaly detection is widely used in a broad range of domains from cybersecurity to manufacturing, finance, and so on. Deep learning based anomaly detection has recently drawn much attention because of its superior capability of recognizing complex data patterns and identifying outliers accurately. However, deep learning models are typically iteratively optimized in a central server with input data gathered from edge devices, and such data transfer between edge devices and the central server impose substantial overhead on the network and incur additional latency and energy consumption. To overcome this problem, we propose a fully-automated, lightweight, statistical learning based anomaly detection framework called LightESD. It is an on-device learning method without the need for data transfer between edge and server, and is extremely lightweight that most low-end edge devices can easily afford with negligible delay, CPU/memory utilization, and power consumption. Yet, it achieves highly competitive detection accuracy. Another salient feature is that it can auto-adapt to probably any dataset without manually setting or configuring model parameters or hyperparameters, which is a drawback of most existing methods. We focus on time series data due to its pervasiveness in edge applications such as IoT. Our evaluation demonstrates that LightESD outperforms other SOTA methods on detection accuracy, efficiency, and resource consumption. Additionally, its fully automated feature gives it another competitive advantage in terms of practical usability and generalizability.

翻译：异常检测广泛应用于从网络安全到制造、金融等众多领域。基于深度学习的异常检测因其在识别复杂数据模式和精确发现异常点方面的卓越能力，近年备受关注。然而，深度学习模型通常是在中央服务器上利用从边缘设备收集的输入数据进行迭代优化，边缘设备与中央服务器之间的数据传输会给网络带来巨大开销，并造成额外的延迟和能耗。为解决此问题，我们提出了一种 fully-automated、轻量级、基于统计学习的异常检测框架 LightESD。它是一种设备端学习方法，无需边缘与服务器之间的数据传输，且极其轻量，以至于大多数低端边缘设备都能轻松负担，并具有可忽略的延迟、CPU/内存占用及功耗。同时，它还能实现极具竞争力的检测精度。另一个显著特点是它能自动适应几乎任何数据集，无需手动设置或配置模型参数或超参数，而这是大多数现有方法的缺点。由于时间序列数据在物联网等边缘应用中普遍存在，我们重点研究此类数据。评估结果表明，LightESD 在检测精度、效率和资源消耗方面均优于其他 SOTA 方法。此外，其 fully-automated 特性使其在实用性和泛化能力方面也具备另一竞争优势。