Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2020-09-28 Cooperative journals: 《计算机应用研究》
Abstract: Fuzzy Test has good applicability in the exploitation of vulnerabilities in industrial control protocols. However, the traditional fuzzy test has the disadvantages of large test workload and a high failure rate. In order to solve these problems, it design an industrial control protocol fuzzy tester GA-fuzzer which combines genetic algorithm and fuzzy test. and propose the concepts of dangerous points and case space model based on dimensional transformation. In GA-fuzzer, it constructed a more efficient dynamic fitness function, and design dynamic mutation and crossover operators to optimize test cases. In the same experimental environment, it used open source fuzzy test method Peach and GA-Fuzzer to test the target. The results show that GA-fuzzer can effectively improve the premature convergence problem of traditional genetic algorithm, and compared to Peach, the number of cases used to achieve the same test expectation was reduced by 27.20% and the test time was reduced by 34.82%.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-08-13 Cooperative journals: 《计算机应用研究》
Abstract: The Modbus industry bus protocol is special. And the network intrusion data sample of industrial control system is not balanced. So this paper used one-class support vector machine (OCSVM) to construct normal OCSVM model and abnormal OCSVM model to simulate the normal mode and abnormal mode of system communication. Then to realize the abnormal detection of industrial control system. In order to prevent the OCSVM model from overfitting and the low accuracy of classification, this paper used the genetic algorithm to the industrial control network by optimizing the dimensionality reduction of the independent variable. This method improves the accuracy of the anomaly detection and reduces the modeling time. Simulation results show that the proposed algorithm is effective for anomaly detection of industrial network.