Datasets
using machine learning
existent ML approaches for anomaly detection
Supervised
Tree-based
- Decision Tree-based algorithms have been used individually to classify some types of attacks: decision tree-based detection of denial of service and command injection attacks
- hybrid classification systems
support-vector machine (SVM)-based
- SVM-based algorithms for anomaly detection: Mehdi Hosseinzadeh, Amir Rahmani, Bay Vo, Moazam Bidaki, Mohammad Masdari, and Mehran Zangakani. Improving security using svmbased anomaly detection: issues and challenges. Soft Computing, 25:1–29, 02 2021.
- binary classification model: Xuedan Miao, Ying Liu, Haiquan Zhao, and Chunguang Li. Distributed online one-class support vector machine for anomaly detection over networks. IEEE Transactions on Cybernetics, 49(4):1475–1488, 2019.
Unsupervised
- K-means clustering algorithm
- Anomaly Detection by Using Streaming K-Means and Batch K-Means
- Hidden Markov Model (HMM)
using Reinforcement Learning
using DL
Hybrid Approaches for Network Anomaly Detection
Reference List
- https://estudogeral.uc.pt/bitstream/10316/102166/4/PedroRafaelBarataNinharelhosTom%c3%a1s.pdf
- Tomás, P. R. B. N. (2022). USING MACHINE LEARNING (ML) FOR ANOMALY DETECTION OVER TRAFFIC PRESENT IN SERVICE MESH ARQUITECTURES (Master’s thesis).
- Soldani, J., & Brogi, A. (2022). Anomaly detection and failure root cause analysis in (micro) service-based cloud applications: A survey. ACM Computing Surveys (CSUR), 55(3), 1-39.