Deep-loglizer

Deep-loglizer — это набор инструментов для анализа журналов на основе глубокого обучения, предназначенный для автоматического обнаружения аномалий.

Если вы используете deep-loglizer в своих исследованиях для публикации, пожалуйста, укажите следующую статью:

Zhuangbin Chen, Jinyang Liu, Wenwei Gu, Yuxin Su, and Michael R. Lyu. Experience Report: Deep Learning-based System Log Analysis for Anomaly Detection. arXiv preprint, arXiv:2107.05908 (2021).

Структура

Deep Learning-based Log Anomaly Detection

Модель	Ссылка на статью
Модели без учителя
LSTM	[CCS'17] Deeplog: Anomaly detection and diagnosis from system logs through deep learning, by Min Du, Feifei Li, Guineng Zheng, and Vivek Srikumar. [University of Utah]
LSTM	[IJCAI'19] LogAnomaly: unsupervised detection of sequential and quantitative anomalies in unstructured logs by Weibin Meng, Ying Liu, Yichen Zhu et al. [Tsinghua University]
Transformer	[ICDM'20] Self-attentive classification-based anomaly detection in unstructured logs, by Sasho Nedelkoski, Jasmin Bogatinovski, Alexander Acker, Jorge Cardoso, and Odej Kao. [TU Berlin]
Autoencoder	[ICT Express'20] Unsupervised log message anomaly detection, by Amir Farzad and T Aaron Gulliver. [University of Victoria]
Модели с учителем
Attentional BiLSTM	[ESEC/FSE'19] Robust log-based anomaly detection on unstable log data by Xu Zhang, Yong Xu, Qingwei Lin et al. [MSRA]
CNN	[DASC'18] Detecting anomaly in big data system logs using convolutional neural network by Siyang Lu, Xiang Wei, Yandong Li, and Liqiang Wang. [University of Central Florida]

git clone https://github.com/logpai/deep-loglizer.git
cd deep-loglizer
pip install -r requirements.txt