ICT Express · 2020 · 116 citations · 32 references
ComputingCloud ComputingComputer ScienceData MiningFeature EngineeringMachine LearningAnomaly DetectionDeep LearningIntrusion DetectionLog AnalysisRepresentation LearningUnsupervised LearningAnomaly Detection In LogsAutoencoder-based Anomaly DetectionIsolationIsolation ForestIsolation-based Anomaly DetectionMachine Learning For Log AnalysisUnsupervised Anomaly DetectionUnsupervised Classification
Log messages are now broadly used in cloud and software systems. They are important for classification and anomaly detection as millions of logs are generated each day. In this paper, an unsupervised model for log message anomaly detection is proposed which employs Isolation Forest and two deep Autoencoder networks. The Autoencoder networks are used for training and feature extraction, and then for anomaly detection, while Isolation Forest is used for positive sample prediction. The proposed model is evaluated using the BGL, Openstack and Thunderbird log message data sets. The results obtained show that the number of negative samples predicted to be positive is low, especially with Isolation Forest and one Autoencoder. Further, the results are better than with other well-known models.
32
Pierre Geurts, Damien Ernst, Louis Wehenkel · Machine Learning · 2006 · 8.7K citations · Full text
Extracting and composing robust features with denoising autoencoders
Pascal Vincent, Hugo Larochelle, Yoshua Bengio et al. · 2008 · 7.3K citations
Fei Tony Liu, Kai Ming Ting, Zhi‐Hua Zhou · 2008 · 5.6K citations
Min Du, Li Fei-Fei, Guineng Zheng et al. · 2017 · 1.6K citations