A Generative Adversarial Networks for Log Anomaly Detection  

作　　者：Xiaoyu Duan Shi Ying Wanli Yuan Hailong Cheng Xiang Yin 

机构地区：[1]School of Computer Science,Wuhan University,Wuhan,430072,China [2]Institute of Information Engineering,Chinese Academy of Sciences,Beijing,100093,China

出　　处：《Computer Systems Science & Engineering》2021年第4期135-148,共14页计算机系统科学与工程（英文）

基　　金：supported by National Natural Science Foundation of China under grant NO.61672392 and NO.61373038;the National Key Research and Development Program of China under grant NO.2016YFC1202204.

摘　　要：Detecting anomaly logs is a great significance step for guarding system faults.Due to the uncertainty of abnormal log types,lack of real anomaly logs and accurately labeled log datasets.Existing technologies cannot be enough for detecting complex and various log point anomalies by using human-defined rules.We propose a log anomaly detection method based on Generative Adversarial Networks(GAN).This method uses the Encoder-Decoder framework based on Long Short-Term Memory(LSTM)network as the generator,takes the log keywords as the input of the encoder,and the decoder outputs the generated log template.The discriminator uses the Convolutional Neural Networks(CNN)to identify the difference between the generated log template and the real log template.The model parameters are optimized automatically by iteration.In the stage of anomaly detection,the probability of anomaly is calculated by the Euclidean distance.Experiments on real data show that this method can detect log point anomalies with an average precision of 95%.Besides,it outperforms other existing log-based anomaly detection methods.

关 键 词：Generative adversarial networks anomaly detection data mining deep learning 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]