Inês Dutra

Abstract

Abstract

Abstract

Abstract
Background Intrusion Tolerant Systems (ITS) aim to maintain system security despite adversarial presence by limiting the impact of successful attacks. Current ITS risk managers rely heavily on public databases like NVD and Exploit DB, which suffer from long delays in vulnerability evaluation, reducing system responsiveness.Objective This work extends the HAL 9000 Risk Manager to integrate additional real-time threat intelligence sources and employ machine learning techniques to automatically predict and reassess vulnerability risk scores, addressing limitations of existing solutions.Methods A custom-built scraper collects diverse cybersecurity data from multiple Open Source Intelligence (OSINT) platforms, such as NVD, CVE, AlienVault OTX, and OSV. HAL 9000 uses machine learning models for CVE score prediction, vulnerability clustering through scalable algorithms, and reassessment incorporating exploit likelihood and patch availability to dynamically evaluate system configurations.Results Integration of newly scraped data significantly enhances the risk management capabilities, enabling faster detection and mitigation of emerging vulnerabilities with improved resilience and security. Experiments show HAL 9000 provides lower risk and more resilient configurations compared to prior methods while maintaining scalability and automation.Conclusions The proposed enhancements position HAL 9000 as a next-generation autonomous Risk Manager capable of effectively incorporating diverse intelligence sources and machine learning to improve ITS security posture in dynamic threat environments. Future work includes expanding data sources, addressing misinformation risks, and real-world deployments.

Abstract
Cloud computing technologies offer significant advantages in scalability and performance, enabling rapid deployment of applications. The adoption of microservices-oriented architectures has introduced an ecosystem characterized by an increased number of applications, frameworks, abstraction layers, orchestrators, and hypervisors, all operating within distributed systems. This complexity results in the generation of vast quantities of logs from diverse sources, making the analysis of these events an inherently challenging task, particularly in the absence of automation. To address this issue, Machine Learning techniques leveraging Large Language Models (LLMs) offer a promising approach for dynamically identifying patterns within these events. In this study, we propose a novel anomaly detection framework utilizing a microservices architecture deployed on Kubernetes and Istio, enhanced by an LLM model. The model was trained on various error scenarios, with Chaos Mesh employed as an error injection tool to simulate faults of different natures, and Locust used as a load generator to create workload stress conditions. After an anomaly is detected by the LLM model, we employ a dynamic Bayesian network to provide probabilistic inferences about the incident, proving the relationships between components and assessing the degree of impact among them. Additionally, a ChatBot powered by the same LLM model allows users to interact with the AI, ask questions about the detected incident, and gain deeper insights. The experimental results demonstrated the model's effectiveness, reliably identifying all error events across various test scenarios. While it successfully avoided missing any anomalies, it did produce some false positives, which remain within acceptable limits.