An Improved Genetic Algorithm and Its Application in Neural Network Adversarial Attack

TL;DR

This paper introduces an improved genetic algorithm with enhanced crossover and mutation strategies, demonstrating superior performance in optimization tasks and effective application in generating neural network adversarial attacks without needing internal model details.

Contribution

The paper proposes a novel genetic algorithm with improved operators and applies it successfully to neural network adversarial attack generation, outperforming existing swarm algorithms.

Findings

The algorithm outperforms three mainstream swarm algorithms on 13 of 15 test functions.

Statistical tests confirm the algorithm's significant advantage at 95% confidence.

It efficiently generates high-confidence adversarial samples without internal neural network information.

Abstract

The choice of crossover and mutation strategies plays a crucial role in the searchability, convergence efficiency and precision of genetic algorithms. In this paper, a novel improved genetic algorithm is proposed by improving the crossover and mutation operation of the simple genetic algorithm, and it is verified by 15 test functions. The qualitative results show that, compared with three other mainstream swarm intelligence optimization algorithms, the algorithm can not only improve the global search ability, convergence efficiency and precision, but also increase the success rate of convergence to the optimal value under the same experimental conditions. The quantitative results show that the algorithm performs superiorly in 13 of the 15 tested functions. The Wilcoxon rank-sum test was used for statistical evaluation, showing the significant advantage of the algorithm at $95\%$ confidence intervals. Finally, the algorithm is applied to neural network adversarial attacks. The applied results show that the method does not need the structure and parameter information inside the neural network model, and it can obtain the adversarial samples with high confidence in a brief time just by the classification and confidence information output from the neural network.