Network Security Risk Assessment Combining Fuzzy Logic and Genetic Algorithm

As network security becomes increasingly important, this paper proposes an Improved-Adaptive Fuzzy Genetic Algorithm (I-AFGA) model that combines fuzzy logic and genetic algorithm for network security risk assessment. The model converts key risk factors into fuzzy linguistic variables, uses a fuzzy rule base for reasoning, and optimizes the parameters and weights of the inference rules through a genetic algorithm. Experimental results show that compared with traditional models, I-AFGA has significantly improved in accuracy (95.0<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">%</sup>), precision (94.0<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">%</sup>), recall (93.7<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">%</sup>) and other indicators, and shows higher stability and reliability in different network environments.