Deep neural networks (DNNs) have been employed in continuous-variable quantum key distribution (CV-QKD) systems as attacking detection portions of defense countermeasures. However, the vulnerability of DNNs leaves security loopholes for hacking attacks, for example, adversarial attacks. In this paper, we propose to implement the one-pixel attack in CV-QKD attack detection networks and accomplish the misclassification on a minimum perturbation. This approach is based on the differential evolution, which makes our attack algorithm fool multiple DNNs with the minimal inner information of target networks. The simulation and experimental results show that, in four different CV-QKD detection networks, , , , and of the input data can be perturbed to another class by modifying just one feature, the same as one pixel for an image. We carry out this success rate in the context of the original accuracy reaching up to nearly on average. Further, by enlarging the number of perturbed features, the success rate can be raised to a satisfactory higher level of about . According to our experimental results, most of the CV-QKD detection networks can be deceived by launching one-pixel attacks.
Machine learning is being applied to continuous-variable quantum key distribution (CVQKD) systems as defense countermeasures for attack classification. However, recent studies have demonstrated that most of these detection networks are not immune to adversarial attacks. In this paper, we propose to implement typical adversarial attack strategies against the CVQKD system and introduce a generalized defense scheme. Adversarial attacks essentially generate data points located near decision boundaries that are linearized based on iterations of the classifier to lead to misclassification. Using the DeepFool attack as an example, we test it on four different CVQKD detection networks and demonstrate that an adversarial attack can fool most CVQKD detection networks. To solve this problem, we propose an improved adversarial perturbation elimination with a generative adversarial network (APE-GAN) scheme to generate samples with similar distribution to the original samples to defend against adversarial attacks. The results show that the proposed scheme can effectively defend against adversarial attacks including DeepFool and other adversarial attacks and significantly improve the security of communication systems.
There exist various attack strategies in continuous-variable quantum key distribution (CVQKD) system in practice. Due to the powerful information processing ability of neural networks, they are applied to the detection and classification of attack strategies in CVQKD systems. However, neural networks are vulnerable to adversarial attacks, resulting in the CVQKD system using neural networks also having security risks. To solve this problem, we propose a defense scheme for the CVQKD system. We first perform low-rank dimensionality reduction on the CVQKD system data through regularized self-representation-locality preserving projects (RSR-LPP) to filter out some adversarial disturbances, and then perform sparse coding reconstruction through dictionary learning to add data details and filter residual adversarial disturbances. We test the proposed defense algorithm in the CVQKD system. The results indicate that our proposed scheme has a good monitoring and alarm effect on CVQKD adversarial disturbances and has a better effect than other compared defense algorithms.
Policy decisions and marketing models have a great impact on the specific application of customer relationship management. In various fields of marketing, big data marketing is gradually popularized as a combined product. The so-called big data marketing refers to collecting a large amount of behavior data through the Internet, primarily helping advertisers find out the target audience to analyze the content, time and form of advertising and finally complete the marketing process of advertising. The big data marketing can also be used for effective customer relationship management, which not only effectively enhance customer stickiness and reduce enterprise operating costs, but also has great significance for deeply mining the potential value of existing customers, predicting the future demand trend of customers, discovering new market growth points and developing new customer groups. Taking the large FMCG company A as the research subject, its sales is grim and stagnant: the purchase quantity of products is low; the price is lower than the cost; simple reproduction is difficult to continue. In order to change the current situation of company A, first of all, we cooperate with the marketing team to determine the business needs, using SQL and python to conduct exploratory data analysis (EDA) on 110k + e-commerce transaction data, and generate Data-Driven Insights on purchasing behavior and product sales; secondly, we use Python to establish RFM model (recent degree, frequency, currency), classify customers and calculate. Finally, according to the above customer analysis, a feasible listing strategy is proposed, which is expected to increase the retention rate by 3.5% and the monthly sales by 6%. Through big data marketing calculation, we come to a solution for the current situation of company A, which will have a good influence on many other companies.
Properly managed urban household waste landfills play a crucial role in achieving sustainable development and ecological civilization. This paper proposes an innovative design method that aims to overcome the limitations and extensive challenges of traditional urban domestic waste landfill design by combining aerial image segmentation with ecological restoration theory. We suggest an enhanced SEVnet, a combination of the basic vnet network and the sequence-and-excitation module, for precise and efficient garbage dump identification. Through this module, the network can independently analyze the significance of each feature channel and provide weights, leading to enhanced image detail recovery and more precise segmentation. We implemented the proposed SEVnet model based on an aerial photography database of urban garbage dumps. Following precise urban garbage disposal site division, we adopt ecological restoration theory to achieve sustainable design. This article presents the Saihanba area in China as a case study, collects pertinent data, and conducts image segmentation and GIS-assisted analysis. This paper examines the landscape application and design of the landfill site based on an analysis and planning of land use in its vicinity. The intervention of landscape ecology imbues the landfill site with new functions. We propose comprehensive planning and landscape restoration design measures from four perspectives, encompassing disadvantages, threats, opportunities, and strengths, using SWOT analysis to better integrate the Hebei Saihanba landfill site with the surrounding environment. This paper introduces a groundbreaking design scheme for a landfill that aligns with the principles of current green and sustainable development.