A Generative Adversarial Networks for Log Anomaly Detection

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

作者机构：School of Computer ScienceWuhan UniversityWuhan430072China Institute of Information EngineeringChinese Academy of SciencesBeijing100093China 

出 版 物：《Computer Systems Science & Engineering》 (计算机系统科学与工程（英文）)

年 卷 期：2021年第37卷第4期

页      面：135-148页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

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 

主　　题：Generative adversarial networks anomaly detection data mining deep learning 

摘      要：Detecting anomaly logs is a great significance step for guarding system *** to the uncertainty of abnormal log types,lack of real anomaly logs and accurately labeled log *** technologies cannot be enough for detecting complex and various log point anomalies by using human-defined *** 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 *** discriminator uses the Convolutional Neural Networks(CNN)to identify the difference between the generated log template and the real log *** model parameters are optimized automatically by *** the stage of anomaly detection,the probability of anomaly is calculated by the Euclidean *** 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.