Search

This paper proposed an optimization method for majority consensus voting algorithm to improve the security of mimic adjudicators . This mimic ruling method based on executive outliers used anomaly detection to directly quantify data reliability to improve voting accuracy. Through constructing the executive body output data set and training the deep learning model, it quantified the abnormal value of the executive body output data. Then, it used the weight optimization algorithm to optimize the weighted distribution of the two parameters. Finally, it selected the optimal weighted result as the voting output result during voting. The experimental results show that the proposed method can improve the accuracy of mimic voting output and has a certain common mode escape detection capability. The optimization model can significantly improve the safety performance of the system. [ABSTRACT FROM AUTHOR]

Black box attack is mainly focuses on the decision information, but there are many query times and the selection of sensitive pixels is difficult. Therefore, this paper proposed a defect sample generation algorithm based on differential evolution. By defining the black box attack as an unconstrained optimization problem, the algorithm used differential evolution to search image sensitive points, and optimized the loss function of decision definition and gradient calculation based on the deep learning model to achieve an effective black box attack. On MNIST and CIF ARlO datasets, the average query times of the proposed algorithm decreased by 28.3% and 14.8% respectively under the same attack success rate. [ABSTRACT FROM AUTHOR]