Cybersecurity threats rapidly affect interdependent systems, making effective defense strategies critical. While several resource allocation frameworks have been proposed, selecting the optimal allocation strategy remains challenging due to the time-consuming nature of naïve and optimization-based methods. This research introduces a meta-learning framework to automatically select the most suitable resource allocation strategy based on system's characteristics. The approach models system vulnerabilities using attack graphs and benchmarks multiple graph-theoretic allocation strategies based on asset ranking. Node features are extracted using Random Walks (RWs) with negative sampling and Stochastic Gradient Descent (SGD). A tabular dataset is constructed using these features and labeled with the optimal allocation strategy. Ten classifiers are trained to predict the best strategy for unseen data. The framework is validated on both real-world and synthetic graphs, outperforming five baselines (including ARGOSMART, ISAC, and Global Best) in security improvement. Using RWs embeddings, our framework outperforms four graph neural network baselines, achieving the highest mean rank. Our model improves security by 42.10% under uniform investments and 43.79% under random investment. We also show that reducing embedding size from 256 to 64 increases security gains. The full implementation is publicly available for further research.

Interdependent systems, with multiple interconnected assets, face escalating cybersecurity threats from external attackers. This article explores security decision-making, operating on complex interdependent systems and proposes a security resource allocation methodology to enhance their proactive security. Using attack graphs, we model vulnerabilities and propose different defense mechanisms integrating different network analysis algorithms, including degree, betweenness, and harmonic centralities, TrustRank, and Katz centrality. We introduce Average Based Node Ranking (ABNR) to average ranks from these methods. The resource allocation methods leverage four different graph-theoretic methods. Each ranking algorithm is combined with these four allocation techniques. Our methods show low sensitivity to simultaneous attacks on interdependent systems. We validate our framework using 11 attack graphs representing real-world systems, measuring security improvements against four well-known allocation algorithms: behavioral decision-making, defense-in-depth, risk-based defense, and min-cut. Our framework outperformed the baselines in most cases, with superior outcomes confirmed by the Friedman statistical test. We show that the main components in our framework have low-time overhead. We also evaluate our framework against multi-stage attacks and cascading failures Our framework enhances security decision-making across different scenarios, including top-1 and all attack paths for different attacks. We release the implementation of our resource allocation methodology to the research community