《异常检测——从经典算法到深度学习》9 异常检测资料汇总（持续更新&抛砖引玉）

smile-yan

已于 2024-05-26 23:42:07 修改

阅读量1.2w

点赞数 80

分类专栏：异常检测文章标签：算法深度学习人工智能

于 2021-03-07 21:59:35 首次发布

本文链接：https://blog.csdn.net/smileyan9/article/details/113728611

版权

异常检测专栏收录该内容

28 篇文章

订阅专栏

这篇博客汇总了多种异常检测算法，包括基于隔离森林、LOF、One-Class SVM、高斯概率密度等经典方法，以及利用VAE、GANs等深度学习技术的最新进展。此外，还提供了数据集、学习资源和开源代码，是研究和实践异常检测的宝贵资料。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

《异常检测——从经典算法到深度学习》

9 异常检测资料汇总（持续更新&抛砖引玉）

考虑到异常检测任务的繁琐，这里特地列举一些可能大家用的到的论文和资料，如果有补充请务必在后面留言。

9.1 论文

论文是重中之重，请务必重视论文阅读。但是在这里很难也不可能列举出所有优秀的论文，所以这里只提供一些常用的查论文的方法等。

此系列论文都保存在阿里云盘，以后的更新也都将同步到这个云盘中。

论文名称	年份	标签	下载地址	源码	个人笔记
Isolation Forest	2009	Isolation Forest/集成学习	蓝奏云	sklearn	CSDN1
LOF: Identifying Density-Based Local Outliers	2000	基于分布密度差异/基于局部计算	蓝奏云	sklearn	CSDN2
Opprentice: Towards Practical and Automatic Anomaly Detection Through Machine Learning	2015	随机森林 / 集成学习 / KPI	netman	\	CSDN5
Variational Autoencoder based Anomaly Detection using Reconstruction Probability	2015	VAE	蓝奏云	\	CSDN6
Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications	2018	VAE / KPI	netman	github	CSDN8
Robust and Unsupervised KPI Anomaly Detection Based on Conditional Variational Autoencoder	2018	cVAE / KPI	netman	github	CSDN10
Rapid Deployment of Anomaly Detection Models for Large Number of Emerging KPI Streams	2018	Framework/集群	netman	\	CSDN11
Unsupervised Anomaly Detection for Intricate KPIs via Adversarial Training of VAE	2019	VAE/GAN	netman	\	CSDN12
Anomaly Detection with Generative AdversarialNetworks for Multivariate Time Series	2018	GAN/RNN/LSTM	arxiv	github	CSDN13
Robust Random Cut Forest Based Anomaly Detection On Streams	2016	随机森林/RRCF	proceedings	github	CSDN14
Practical and White-Box Anomaly Detection through Unsupervised and Active Learning	2020	随机森林/RRCF	netman	\	CSDN15
Unsupervised Anomaly Detection with Variational Auto-Encoder and Local Outliers Factor for KPIs	2021	VAE / LOF	ISPA	\	CSDN16
ANOMALY DETECTION FOR TIME SERIES USING VAE-LSTM HYBRID MODEL	2020	VAE-LSTM	ICASSP	\	CSDN17
USAD : UnSupervised Anomaly Detection on Multivariate Time Series	2020	adversely AutoEncoder	research gate	\	CSDN18
Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network	2019	RNN	KDD 19	github	CSDN19
HotSpot: Anomaly Localization for Additive KPIs with Multi-Dimensional Attributes	2018	蒙特卡罗搜索树	IEEE Access netman	\	CSDN20
ANOMALY TRANSFORMER: TIME SERIES ANOMALY DETECTION WITH ASSOCIATION DISCREPANCY	2022	Transformer	ICLR arxiv	github	CSDN21
Identifying Erroneous Software Changes through Self-Supervised Contrastive Learning on Time Series Data	2022	LSTM	ISSRE netman	github	CSDN22
TIMESNET: TEMPORAL 2D-VARIATION MODELING FOR GENERAL TIME SERIES ANALYSIS	2023	/	ICLR2023	github	CSDN23
TSB-UAD: an end-to-end benchmark suite for univariate time-series anomaly detection	2023	/	VLDB	github	CSDN24
Deep Isolation Forest for Anomaly Detection	2023	Deep IF	TKDE arxiv	github	CSDN25
Time-LLM: Time Series Forecasting by Reprogramming Large Language Models	2024	LLM	arxiv	github	CSDN26
Actionable and Interpretable Fault Localization for Recurring Failures in Online Service Systems	2022	FDG, GAT	netman	CSDN27

9.2 数据集

这个是特别需要关注的地方，因为没有数据集就没法做实验，没有数据集是一个非常严重的问题。到目前为止能够直接使用的数据集也很少。

其他数据集：

iTrust 数据集（以下内容均来自iTrust官方回复的邮件，一般最新的也会存储与此云盘）：

SWaT

ITEM	链接
SWaT.A1 & A2_Dec 2015	https://drive.google.com/drive/folders/1xTNQDqEFtFfDuhl75P23ZNIeGgCntRt7?usp=sharing
SWaT.A3_Jun 2017	https://drive.google.com/drive/folders/1hcowKm_VtU_Q5HY-jRsiaoKl8IGYGQQj?usp=sharing
SWaT.A4 & A5_Jul 2019	https://drive.google.com/drive/folders/1OD2DSt4T-3WysolSLCda7hNYnoc62Mtq?usp=sharing
SWaT.A6_Dec 2019	https://drive.google.com/drive/folders/188nwa2EYofof4X2KgDNEav2WtmEN4YBn?usp=sharing
SWaT.A7_Jun 2020	https://drive.google.com/drive/folders/1LRU4R8Szec3jO31YX2cI5qO-ToZ3WUkv?usp=sharing
ALL	https://drive.google.com/drive/folders/1ABZKdclka3e2NXBSxS9z2YF59p7g2Y5I?usp=sharing

WADI

ITEM	链接
WADI.A1_9 Oct 2017	https://drive.google.com/drive/folders/1-4WJfyLTIC1QBdUXMecols_bRCuCqwYW?usp=sharing
WADI.A2_19 Nov 2019	https://drive.google.com/drive/folders/12mqpuejSSjq2Wa_0muVjcoQuLN0H6vZt?usp=sharing
All	https://drive.google.com/drive/folders/11XWMQruwxFvlVEiqNgZ1mxVw-c-5xSmR?usp=sharing

EPIC

https://drive.google.com/drive/folders/1WdWIOSM2E2bLPl9wAUFLlaZUWSa3M3RF?usp=sharing

CISS

ITEM	链接
S317	https://drive.google.com/drive/folders/1prgaDr7TC0v0ln5M-0RFUjhOMnMsQ8dm?usp=sharing
CISS 2019	https://drive.google.com/drive/folders/11jmDoCTFTX9oy2BthxQXOrzQg8DsZNpM?usp=sharing
All	https://drive.google.com/drive/folders/1k8RE8XXwxaFZXwQ7qmvnHLJZL2kaLISy?usp=sharing

Blaq_0
https://drive.google.com/drive/folders/1fkgwxT9zwxlbpZ-mpLuPYRv7DcQ2ljek?usp=sharing

BATADAL
https://drive.google.com/drive/folders/12-nEv4WaPlgj6SYb-vc7tBFrwxNSWjaV?usp=sharing

9.3 学习资源

华为云学院提供了微认证，推荐新手了解一下。

NAIE日志异常检测服务应用 https://edu.huaweicloud.com/certifications/78d55ca9c9fa4b40b73f7979ffab9a43
NAIE KPI异常检测模型服务应用 https://edu.huaweicloud.com/certifications/3310e5169bf54940bf644d0201ab7013