An Improved Genetic Algorithm and Its Application in Neural Network Adversarial Attack
This work addresses optimization challenges in genetic algorithms and adversarial attacks for neural networks, representing an incremental improvement with specific gains.
The paper proposes an improved genetic algorithm that enhances global search ability, convergence efficiency, and precision, outperforming other algorithms in 13 out of 15 test functions, and applies it to neural network adversarial attacks to generate high-confidence adversarial samples quickly without needing internal model details.
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.