A multi-objective genetic algorithm for minimising network security risk and cost

Viduto, Valentina; Maple, Carsten; Huang, Wei; Bochenkov, Alexey

doi:10.1109/hpcsim.2012.6266959

Cited by 13 publications

(12 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As can be seen from Table 2, the maximum relative error between the output of the network and the expected output value is 5.17%, and the minimum relative error is 1.38%. Under the same settings, compared with the literature [7], the literature [8] and the literature [9], the average error of the method is also the smallest (see Fig. 6).…”

Section: Experiments and Analysismentioning

confidence: 86%

“…The ambiguity of expression and the heterogeneity of the plan system, etc., cannot be organically unified between different emergency plan systems [6]. The literature [7] proposed a multi-objective genetic algorithm (MOGA) method, offline optimization routines to deploy genetic algorithms to search for the best combination of strategies, while considering multiple risk factors, from the PTA (practical threat analysis) case study The real world data was tested to show that our approach can provide solutions for real-world problem data sets. Literature [8] proposed an information system security risk assessment method, which is applied to group decision and analytic process methods.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A security risk plan search assistant decision algorithm using deep neural network combined with two-stage similarity calculation

Fang

et al. 2019

Pers Ubiquit Comput

View full text Add to dashboard Cite

In view of the nonlinearity and uncertainty of safety accident risk assessment, firstly, based on the deep neural network, the training criterion of the network is changed, and the triplet convolutional neural network with the similarity measure as the cost function is proposed. The inactive multi-scale set features are extracted from them, so that the semantic features obtained by learning are suitable for security risk image retrieval. In the image retrieval application, the training samples of the retrieved data set are not enough to train a large network, and the innovative application of migration learning to security risk image retrieval proposes to train the network with data sets similar to the retrieved data sets. Then based on the traditional nearest neighbor algorithm, this paper proposes a case similarity calculation method based on two-dimensional structure of structural similarity and attribute similarity, input the characteristic attribute value of the current emergency event, and conduct similar case retrieval. The final calculation returns the historical case and its solution that the user is most similar to the currently entered incident feature. The experiment proves that the maximum relative error between the output of the network and the expected output value is 5.17%, and the minimum relative error is 1.38%, which has high accuracy.

show abstract

Section: Experiments and Analysismentioning

confidence: 86%

Section: Introductionmentioning

confidence: 99%

A security risk plan search assistant decision algorithm using deep neural network combined with two-stage similarity calculation

Fang

et al. 2019

Pers Ubiquit Comput

View full text Add to dashboard Cite

show abstract

“…Moreover, a genetic algorithm was adopted to choose the minimal-cost security profile providing the maximal vulnerability coverage. Ref [17] demonstrated a model of quantitative risk analysis, and deplyed a genetic algorithm to search for the best countermeasure combination, while multiple risk factors are considered. Apart from genetic algorithm, efforts have been spent to seek for more possibilities of solving the problem.…”

Section: Related Workmentioning

confidence: 99%

“…Moreover, it's convenient for the optimal set to cooperate with different security goals and hardening constraints, because defenders can choose specific solutions flexibly from the optimal set to address practical security problems. Compare with previous works which also adopt genetic algorithms to work out the problem, such as [8] [17] and [20], our method have three major differences. First, our multi-objective model is constructed on the basis of simplified risk flow attack graph rather than complex attack trees or attack graphs.…”

Section: Related Workmentioning

confidence: 99%

Using Genetic Algorithm for Optimal Security Hardening in Risk Flow Attack Graph

2015

KSII TIIS

View full text Add to dashboard Cite

Network environment has been under constant threat from both malicious attackers and inherent vulnerabilities of network infrastructure. Existence of such threats calls for exhaustive vulnerability analyzing to guarantee a secure system. However, due to the diversity of security hazards, analysts have to select from massive alternative hardening strategies, which is laborious and time-consuming. In this paper, we develop an approach to seek for possible hardening strategies and prioritize them to help security analysts to handle the optimal ones. In particular, we apply a Risk Flow Attack Graph (RFAG) to represent network situation and attack scenarios, and analyze them to measure network risk. We also employ a multi-objective genetic algorithm to infer the priority of hardening strategies automatically. Finally, we present some numerical results to show the performance of prioritizing strategies by network risk and hardening cost and illustrate the application of optimal hardening strategy set in typical cases. Our novel approach provides a promising new direction for network and vulnerability analysis to take proper precautions to reduce network risk.

show abstract

“…The method is based on an application of Genetic Algorithms (GA) to the FFIP framework. In the previous applications of GA to security, computing and physical properties of the system under attack were not explicitly modelled and simulated, since expert judgment has been used to provide data for the algorithm to operate on instead of simulation [25] while [26] requires historical data or other knowledge sources about system vulnerabilities as input. In this paper, only a simulation model of the system is required, and the method is demonstrated with a detailed simulation of a generic pressurized nuclear water reactor model.…”

Section: System Simulation For Security Impact Assessmentmentioning

confidence: 99%

Security impact assessment of industrial automation systems using genetic algorithm and simulation

Papakonstantinou

Sierla

Charitoudi

et al. 2014

Proceedings of the 2014 IEEE Emerging Technology and Factory Automation (ETFA)

View full text Add to dashboard Cite

Much of the research on security of industrial automation systems has focused on countermeasures such as intrusion detection, certificate management or public key infrastructures. Due to limited resources, countermeasures should be focused to prevent the attacks with highest potential for damage. The impact of an attack can only be determined through a detailed analysis of the interactions of the automation system and the physical system under control. Attacks against single components are similar to ordinary component failures, so our focus is on deliberate damage to several components, since such scenarios are not considered in reliability engineering methods used for industrial automation systems. A simulation based security impact assessment method is proposed, using genetic algorithms to explore the range of possible attacks.

show abstract

A multi-objective genetic algorithm for minimising network security risk and cost

Cited by 13 publications

References 10 publications

A security risk plan search assistant decision algorithm using deep neural network combined with two-stage similarity calculation

A security risk plan search assistant decision algorithm using deep neural network combined with two-stage similarity calculation

Using Genetic Algorithm for Optimal Security Hardening in Risk Flow Attack Graph

Security impact assessment of industrial automation systems using genetic algorithm and simulation

Contact Info

Product

Resources

About