FORECASTING MULTI-STAGE ATTACKS IN KUBERNETES FROM FALCO ALERTS USING STATE-SPACE MODELS
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
The article discusses the problem of proactive detection and forecasting of multi-stage cyberattacks in Kubernetes clusters based on the analysis of security event streams. As a mathematical framework, the use of Selective State-Space Models (SSM) is proposed, which allows for effective processing of long sequences of Falco alerts, taking into account the context of system calls and orchestrator metadata. It is demonstrated that the developed architecture outperforms baseline recurrent neural networks (LSTM/GRU) in the task of binary incident classification, achieving a ROC-AUC score of 0.93 and an F1-score of 0.84 on a test dataset generated using MITRE ATT&CK scenarios. It is established that the proposed method enables early threat detection (on average at 57% of the attack episode length), which facilitates the application of proactive response mechanisms, such as container migration, before critical consequences occur.
Fields of Study & Subjects
Network Security and Intrusion Detection
Software System Performance and Reliability
Security and Verification in Computing
Publication details
- Journal / source
- Problems of information security Computer systems
- Volume
- 68
- Issue
- 1
- Pages
- 58–68
- Publication date
- 1 January 2026
- Language
- EN