Search

In this paper, we propose an Iterative Greedy-Universal Adversarial Perturbations (IGUAP) approach based on an iterative greedy algorithm to create universal adversarial perturbations for acoustic prints. A thorough, objective account of the IG-UAP method is provided, outlining its framework and approach. The method leverages a greedy iteration approach to formulate an optimization problem for solving acoustic universal adversarial perturbations, with a new objective function designed to ensure that the attack has higher accuracy in terms of minimizing the perceptibility of adversarial perturbations and increasing the accuracy of successful attacks. The perturbation generation process is described in detail, and the resulting acoustic universal adversarial perturbation is evaluated in both target-attack and no-target-attack scenarios. Experimental analysis and testing were carried out using comparable techniques and dissimilar target models. The findings reveal that the acoustic generality adversarial perturbation produced by the IG-UAP method can obtain effective attack results even when the audio training data sample size is minimal, i.e., one for each category. Moreover, the human ear finds it difficult to detect the loss of original data information and the addition of adversarial perturbation (for the case of a target attack, the ASR values range from 82.4% to 90.2% for the small sample data set). The success rates for untargeted and targeted attacks average 85.8% and 84.9%, respectively. [ABSTRACT FROM AUTHOR]

To address the problems of the single evolutionary approach, decreasing diversity, inhomogeneity, and meaningfulness in the destruction process when the teaching–learning-based optimization (TLBO) algorithm solves the no-wait flow-shop-scheduling problem, the multi-strategy discrete teaching–learning-based optimization algorithm (MSDTLBO) is introduced. Considering the differences between individuals, the algorithm is redefined from the student's point of view, giving the basic integer sequence encoding. To address the fact that the algorithm is prone to falling into local optimum and to leading to a reduction in search accuracy, the population was divided into three groups according to the learning ability of the individuals, and different teaching strategies were adopted to achieve the effect of teaching according to their needs. To improve the destruction-and-reconstruction process with symmetry, an iterative greedy algorithm of destruction–reconstruction was used as the main body, and a knowledge base was used to control the number of meaningless artifacts to be destroyed and to dynamically change the artifact-selection method in the destruction process. Finally, the algorithm was applied to the no-wait flow-shop-scheduling problem (NWFSP) to test its practical application value. After comparing twenty-one benchmark test functions with six algorithms, the experimental results showed that the algorithm has a certain effectiveness in solving NWFSP. [ABSTRACT FROM AUTHOR]

In this paper, we propose an Iterative Greedy-Universal Adversarial Perturbations (IGUAP) approach based on an iterative greedy algorithm to create universal adversarial perturbations for acoustic prints. A thorough, objective account of the IG-UAP method is provided, outlining its framework and approach. The method leverages a greedy iteration approach to formulate an optimization problem for solving acoustic universal adversarial perturbations, with a new objective function designed to ensure that the attack has higher accuracy in terms of minimizing the perceptibility of adversarial perturbations and increasing the accuracy of successful attacks. The perturbation generation process is described in detail, and the resulting acoustic universal adversarial perturbation is evaluated in both target-attack and no-target-attack scenarios. Experimental analysis and testing were carried out using comparable techniques and dissimilar target models. The findings reveal that the acoustic generality adversarial perturbation produced by the IG-UAP method can obtain effective attack results even when the audio training data sample size is minimal, i.e., one for each category. Moreover, the human ear finds it difficult to detect the loss of original data information and the addition of adversarial perturbation (for the case of a target attack, the ASR values range from 82.4% to 90.2% for the small sample data set). The success rates for untargeted and targeted attacks average 85.8% and 84.9%, respectively.

To address the problems of the single evolutionary approach, decreasing diversity, inhomogeneity, and meaningfulness in the destruction process when the teaching–learning-based optimization (TLBO) algorithm solves the no-wait flow-shop-scheduling problem, the multi-strategy discrete teaching–learning-based optimization algorithm (MSDTLBO) is introduced. Considering the differences between individuals, the algorithm is redefined from the student’s point of view, giving the basic integer sequence encoding. To address the fact that the algorithm is prone to falling into local optimum and to leading to a reduction in search accuracy, the population was divided into three groups according to the learning ability of the individuals, and different teaching strategies were adopted to achieve the effect of teaching according to their needs. To improve the destruction-and-reconstruction process with symmetry, an iterative greedy algorithm of destruction–reconstruction was used as the main body, and a knowledge base was used to control the number of meaningless artifacts to be destroyed and to dynamically change the artifact-selection method in the destruction process. Finally, the algorithm was applied to the no-wait flow-shop-scheduling problem (NWFSP) to test its practical application value. After comparing twenty-one benchmark test functions with six algorithms, the experimental results showed that the algorithm has a certain effectiveness in solving NWFSP.