AISGA: Multi-objective parameters optimization for countermeasures selection through genetic algorithm

Abstract

Cyberattacks targeting modern network infrastructures are increasing in number and impact. This growing phenomenon emphasizes the central role of cybersecurity and, in particular, the reaction against ongoing threats targeting assets within the protected system. Such centrality is reflected in the literature, where several works have been presented to propose full-fledged reaction methodologies to tackle offensive incidents' consequences. In this direction, the work in [18] developed an immuno-based response approach based on the application of the Artificial Immune System (AIS) methodology. That is, the AIS-powered reaction is able to calculate the optimal set of atomic countermeasure to enforce on the asset within the monitored system, minimizing the risk to which those are exposed in a more than adequate time. To further contribute to this line, the paper at hand presents AISGA, a multi-objective approach that leverages the capabilities of a Genetic Algorithm (GA) to optimize the selection of the input parameters of the AIS methodology. Specifically, AISGA selects the optimal ranges of inputs that balance the tradeoff between minimizing the global risk and the execution time of the methodology. Additionally, by flooding the AIS-powered reaction with a wide range of possible inputs, AISGA intends to demonstrate the robustness of such a model. Exhaustive experiments are executed to precisely compute the optimal ranges of parameters, demonstrating that the proposed multi-objective optimization prefers a fast-but-effective reaction.

Intrusion Response Systems for the 5G Networks and Beyond: A New Joint Security-vs-QoS Optimization Approach

“…They, however, suggested a context-aware stop condition based on experimental outcomes and authors' subjective beliefs. In [17] the authors further improved the previous work by proposing an AISGA method leveraging a GA to optimize the selection of input parameters of the AIS method by minimizing the global risk and the execution time of the method.…”

“…Fig.7depicts the impact of Constraint(17) on the joint objective, QoS, and security of the two ASM and CSM algorithms. This figure is the average result of 500 simulation experiments, where we relax A = 10, C = 4, ξ = 6, and β i = 0.33.There are mainly two points that can be observed from the figures.…”

Enhancing the Efficiency of a Cyber SOC Using Biomimetic Algorithms Empowered by Deep Q–Learning

“…The rising frequency and severity of cyberattacks underscore the essential role of cybersecurity in protecting organizational assets. Research such as the study by [15] introduces a groundbreaking multi-objective optimization approach for cybersecurity countermeasures using Genetic Algorithms. This methodology aims to fine-tune Artificial Immune System parameters to achieve an ideal balance between minimizing risk and optimizing execution time.…”

“…Finally, learning in DQL is governed by a loss function according to Equation (15), which measures the discrepancy between the estimated Q and target values.…”

Enhancing the Efficiency of a Cybersecurity Operations Center Using Biomimetic Algorithms Empowered by Deep Q-Learning

“…The rising frequency and severity of cyberattacks underscore the essential role of cybersecurity in protecting organizational assets. Research such as the study by [ 15 ] introduces a groundbreaking multi-objective optimization approach for cybersecurity countermeasures using Genetic Algorithms. Their methodology aims to fine-tune Artificial Immune System parameters to achieve an ideal balance between minimizing risk and optimizing execution time.…”