SPARK: Secure Predictive Autoscaling for Robust Kubernetes
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918413542096896 |
|---|---|
| author | Jiang, Zhijun Fard, Amin Milani |
| author_facet | Jiang, Zhijun Fard, Amin Milani |
| contents | Achieving high availability and robust security in Kubernetes requires more than reactive scaling and standard perimeter firewalls. Traditional autoscalers, such as HPA, often fail to react quickly to traffic spikes and cannot distinguish between legitimate flash crowds and DDoS attacks. We present an open-source toolchain to provide a traffic-aware autoscaling approach that utilizes an eBPF-based networking layer to enforce security policies at the kernel level while orchestrating scaling decisions based on predictive models. Our results demonstrate that the predictive approach reduces timeout errors by 32% during sudden traffic surges compared to standard reactive scaling, while ensuring immediate network convergence and layer 7 security isolation for newly scaled pods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_26833 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SPARK: Secure Predictive Autoscaling for Robust Kubernetes Jiang, Zhijun Fard, Amin Milani Cryptography and Security Achieving high availability and robust security in Kubernetes requires more than reactive scaling and standard perimeter firewalls. Traditional autoscalers, such as HPA, often fail to react quickly to traffic spikes and cannot distinguish between legitimate flash crowds and DDoS attacks. We present an open-source toolchain to provide a traffic-aware autoscaling approach that utilizes an eBPF-based networking layer to enforce security policies at the kernel level while orchestrating scaling decisions based on predictive models. Our results demonstrate that the predictive approach reduces timeout errors by 32% during sudden traffic surges compared to standard reactive scaling, while ensuring immediate network convergence and layer 7 security isolation for newly scaled pods. |
| title | SPARK: Secure Predictive Autoscaling for Robust Kubernetes |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2603.26833 |