Lijun Gao, Kai Liu, Wenjun Liu, Jiehong Wu, Xiao Jin
As machine learning models become increasingly integrated into practical applications and are made accessible via public APIs, the risk of model extraction attacks has gained prominence. This study presents an innovative and efficient approach to model extraction attacks, aimed at reducing query costs and enhancing attack effectiveness. The method begins by leveraging a pre-trained model to identify high-confidence samples from unlabeled datasets. It then employs unsupervised contrastive learning to thoroughly dissect the structural nuances of these samples, constructing a dataset of high quality that precisely mirrors a variety of features. A mixed information confidence strategy is employed to refine the query set, effectively probing the decision boundaries of the target model. By integrating consistency regularization and pseudo-labeling techniques, reliance on authentic labels is minimized, thus improving the feature extraction capabilities and predictive precision of the surrogate models. Evaluation on four major datasets reveals that the models crafted through this method bear a close functional resemblance to the original models, with a real-world API test success rate of 62.35%, which vouches for the method’s validity.
随着机器学习模型越来越多地集成到实际应用中，并可通过公共应用程序接口访问，模型提取攻击的风险日益突出。本研究针对模型提取攻击提出了一种创新而高效的方法，旨在降低查询成本并提高攻击效果。该方法首先利用预先训练好的模型，从未标明的数据集中识别出高信度样本。然后，它采用无监督对比学习，彻底剖析这些样本结构上的细微差别，构建一个精确反映各种特征的高质量数据集。采用混合信息置信策略来完善查询集，从而有效探测目标模型的决策边界。通过整合一致性正则化和伪标签技术，最大限度地减少了对真实标签的依赖，从而提高了特征提取能力和代用模型的预测精度。在四个主要数据集上进行的评估表明，通过这种方法制作的模型在功能上与原始模型非常相似，实际 API 测试成功率高达 62.35%，这证明了该方法的有效性。
{"title":"Model extraction via active learning by fusing prior and posterior knowledge from unlabeled data","authors":"Lijun Gao, Kai Liu, Wenjun Liu, Jiehong Wu, Xiao Jin","doi":"10.3233/jifs-239504","DOIUrl":"https://doi.org/10.3233/jifs-239504","url":null,"abstract":"As machine learning models become increasingly integrated into practical applications and are made accessible via public APIs, the risk of model extraction attacks has gained prominence. This study presents an innovative and efficient approach to model extraction attacks, aimed at reducing query costs and enhancing attack effectiveness. The method begins by leveraging a pre-trained model to identify high-confidence samples from unlabeled datasets. It then employs unsupervised contrastive learning to thoroughly dissect the structural nuances of these samples, constructing a dataset of high quality that precisely mirrors a variety of features. A mixed information confidence strategy is employed to refine the query set, effectively probing the decision boundaries of the target model. By integrating consistency regularization and pseudo-labeling techniques, reliance on authentic labels is minimized, thus improving the feature extraction capabilities and predictive precision of the surrogate models. Evaluation on four major datasets reveals that the models crafted through this method bear a close functional resemblance to the original models, with a real-world API test success rate of 62.35%, which vouches for the method’s validity.","PeriodicalId":509313,"journal":{"name":"Journal of Intelligent & Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140230004","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Tao Li, Zhongyu Zhang, Zhigang Tao, Xinyu Jia, Xiaolong Wang, Jian Wang
Rock crack is one of the main factors responsible for rock failure. Uniaxial compression creep tests are performed using acoustic emission techniques, a high-sensitivity, non-radiative, non-destructive testing method to understand the influence of crack number on the precursor characteristics of short-term creep damage in the fractured rock mass. Based on the Grassberger-Procaccia (G-P) algorithm, the calculation step size for the correlation dimension value (D 2) of the acoustic emission ringing count rate is consistent with that for the acoustic emission b-value. The influence of the number of pre-cracks on the Acoustic emission precursor characteristics of red sandstone creep is analyzed. The results show that near the destabilization of the specimen, the Acoustic emission accumulative ringing count surges in a stepwise manner, the Acoustic emission b-value decreases, the D 2-value increases, the Acoustic emission amplitude shows high intensity and high frequency, and the ringing count increases sharply, all with the characteristics of failure precursors. During the accelerated creep stage of the specimens, with the increase of pre-cracks number, the precursory time points of acoustic emission b-value and D 2-value advance, and their acoustic emission ringing counts increase sharply.
岩石裂缝是造成岩石破坏的主要因素之一。利用声发射技术这种高灵敏度、非辐射、无损检测方法进行单轴压缩蠕变试验，以了解裂缝数量对断裂岩体短期蠕变破坏前兆特征的影响。基于 Grassberger-Procaccia (G-P) 算法，声发射振铃计数率相关维度值 (D 2) 的计算步长与声发射 b 值的计算步长一致。分析了前裂缝数量对红砂岩蠕变声发射前兆特征的影响。结果表明，在试样失稳附近，声发射累积振铃数呈阶梯状激增，声发射 b 值减小，D 2 值增大，声发射振幅呈现高强度和高频率，振铃数急剧增加，这些都具有破坏前兆的特征。在试样的加速蠕变阶段，随着预裂纹数量的增加，声发射 b 值和 D 2 值的前兆时间点提前，声发射振铃数急剧增加。
{"title":"Investigation of the influence of pre-crack number on acoustic emission characterization of red-sandstone short-term creep damage and failure precursors","authors":"Tao Li, Zhongyu Zhang, Zhigang Tao, Xinyu Jia, Xiaolong Wang, Jian Wang","doi":"10.3233/jifs-238964","DOIUrl":"https://doi.org/10.3233/jifs-238964","url":null,"abstract":"Rock crack is one of the main factors responsible for rock failure. Uniaxial compression creep tests are performed using acoustic emission techniques, a high-sensitivity, non-radiative, non-destructive testing method to understand the influence of crack number on the precursor characteristics of short-term creep damage in the fractured rock mass. Based on the Grassberger-Procaccia (G-P) algorithm, the calculation step size for the correlation dimension value (D 2) of the acoustic emission ringing count rate is consistent with that for the acoustic emission b-value. The influence of the number of pre-cracks on the Acoustic emission precursor characteristics of red sandstone creep is analyzed. The results show that near the destabilization of the specimen, the Acoustic emission accumulative ringing count surges in a stepwise manner, the Acoustic emission b-value decreases, the D 2-value increases, the Acoustic emission amplitude shows high intensity and high frequency, and the ringing count increases sharply, all with the characteristics of failure precursors. During the accelerated creep stage of the specimens, with the increase of pre-cracks number, the precursory time points of acoustic emission b-value and D 2-value advance, and their acoustic emission ringing counts increase sharply.","PeriodicalId":509313,"journal":{"name":"Journal of Intelligent & Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140228737","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sensors are often deployed in harsh environments, in which some threats may endanger the safety of sensors. In this paper, a sensor deployment model is developed in Wireless Sensor Networks (WSNs), in which the coverage rate and the threat risk are considered simultaneously. The model is established as an optimization problem. An adaptive ranking teaching learning-based optimization algorithm (ARTLBO) is proposed to solve the problem. Learners are divided into inferior and superior groups. The teacher phase is boosted by replacing the teacher with the top three learners, and the learner phase is improved by providing some guidance for inferior learners. The experimental results show that the proposed ARTLBO algorithm can effectively optimize the model. The fitness values of the proposed model found by the proposed ARTLBO are 0.4894, 0.4886, which are better than its competitors. The algorithm can provide a higher coverage rate and lower threat risk.
{"title":"An adaptive ranking teaching learning-based optimization algorithm to solve sensor deployment in harsh environments","authors":"Xiaobing Yu, Yuexin Zhang, Xuming Wang","doi":"10.3233/jifs-240215","DOIUrl":"https://doi.org/10.3233/jifs-240215","url":null,"abstract":"Sensors are often deployed in harsh environments, in which some threats may endanger the safety of sensors. In this paper, a sensor deployment model is developed in Wireless Sensor Networks (WSNs), in which the coverage rate and the threat risk are considered simultaneously. The model is established as an optimization problem. An adaptive ranking teaching learning-based optimization algorithm (ARTLBO) is proposed to solve the problem. Learners are divided into inferior and superior groups. The teacher phase is boosted by replacing the teacher with the top three learners, and the learner phase is improved by providing some guidance for inferior learners. The experimental results show that the proposed ARTLBO algorithm can effectively optimize the model. The fitness values of the proposed model found by the proposed ARTLBO are 0.4894, 0.4886, which are better than its competitors. The algorithm can provide a higher coverage rate and lower threat risk.","PeriodicalId":509313,"journal":{"name":"Journal of Intelligent & Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140231117","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Candlesticks are widely used as an effective technical analysis tool in financial markets. Traditionally, different combinations of candlesticks have formed specific bullish/bearish patterns providing investors with increased opportunities for profitable trades. However, most patterns derived from subjective expertise without quantitative analysis. In this article, combining bullish/bearish patterns with ensemble learning, we present an intelligent system for making stock trading decisions. The Ensemble Classifier through Multimodal Perturbation (ECMP) is designed to generate a diverse set of precise base classifiers to further determine the candlestick patterns. It achieves this by: first, introducing perturbations to the sample space through bootstrap sampling; second, employing an attribute reduction algorithm based on neighborhood rough set theory to select relevant features; third, perturbing the feature space through random subspace selection. Ultimately, the trading decisions are guided by the classification outcomes of this procedure. To evaluate the proposed model, we apply it to empirical investigations within the context of the Chinese stock market. The results obtained from our experiments clearly demonstrate the effectiveness of the approach.
{"title":"An intelligent stock trading decision system based on ensemble classifier through multimodal perturbation","authors":"Xiaoyu Hou, Chao Luo, Baozhong Gao","doi":"10.3233/jifs-237087","DOIUrl":"https://doi.org/10.3233/jifs-237087","url":null,"abstract":"Candlesticks are widely used as an effective technical analysis tool in financial markets. Traditionally, different combinations of candlesticks have formed specific bullish/bearish patterns providing investors with increased opportunities for profitable trades. However, most patterns derived from subjective expertise without quantitative analysis. In this article, combining bullish/bearish patterns with ensemble learning, we present an intelligent system for making stock trading decisions. The Ensemble Classifier through Multimodal Perturbation (ECMP) is designed to generate a diverse set of precise base classifiers to further determine the candlestick patterns. It achieves this by: first, introducing perturbations to the sample space through bootstrap sampling; second, employing an attribute reduction algorithm based on neighborhood rough set theory to select relevant features; third, perturbing the feature space through random subspace selection. Ultimately, the trading decisions are guided by the classification outcomes of this procedure. To evaluate the proposed model, we apply it to empirical investigations within the context of the Chinese stock market. The results obtained from our experiments clearly demonstrate the effectiveness of the approach.","PeriodicalId":509313,"journal":{"name":"Journal of Intelligent & Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140229078","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Personalized recommendation systems fundamentally assess user preferences as a reflection of their emotional responses to items. Traditional recommendation algorithms, focusing primarily on numerical processing, often overlook emotional factors, leading to reduced accuracy and limited application scenarios. This paper introduces a collaborative filtering recommendation method that integrates features of facial information, derived from emotions extracted from such data. Upon user authorization for camera usage, the system captures facial information features. Owing to the diversity in facial information, deep learning methods classify these features, employing the classification results as emotional labels. This approach calculates the similarity between emotional and item labels, reducing the ambiguity inherent in facial information features. The fusion process of facial information takes into account the user’s emotional state prior to item interaction, which might influence the emotions generated during the interaction. Variance is utilized to measure emotional fluctuations, thereby circumventing misjudgments caused by sustained non-interactive emotions. In selecting the nearest neighboring users, the method considers not only the similarity in user ratings but also in their emotional responses. Tests conducted using the Movielens dataset reveal that the proposed method, modeling facial features, more effectively aligns recommendations with user preferences and significantly enhances the algorithm’s performance.
{"title":"A collaborative filtering method by fusion of facial information features","authors":"Shuo Wang, Jing Yang, Yue Yang","doi":"10.3233/jifs-232718","DOIUrl":"https://doi.org/10.3233/jifs-232718","url":null,"abstract":"Personalized recommendation systems fundamentally assess user preferences as a reflection of their emotional responses to items. Traditional recommendation algorithms, focusing primarily on numerical processing, often overlook emotional factors, leading to reduced accuracy and limited application scenarios. This paper introduces a collaborative filtering recommendation method that integrates features of facial information, derived from emotions extracted from such data. Upon user authorization for camera usage, the system captures facial information features. Owing to the diversity in facial information, deep learning methods classify these features, employing the classification results as emotional labels. This approach calculates the similarity between emotional and item labels, reducing the ambiguity inherent in facial information features. The fusion process of facial information takes into account the user’s emotional state prior to item interaction, which might influence the emotions generated during the interaction. Variance is utilized to measure emotional fluctuations, thereby circumventing misjudgments caused by sustained non-interactive emotions. In selecting the nearest neighboring users, the method considers not only the similarity in user ratings but also in their emotional responses. Tests conducted using the Movielens dataset reveal that the proposed method, modeling facial features, more effectively aligns recommendations with user preferences and significantly enhances the algorithm’s performance.","PeriodicalId":509313,"journal":{"name":"Journal of Intelligent & Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140229627","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yi Ning, Meiyu Liu, Xifeng Guo, Zhiyong Liu, Xinlu Wang
Accurate load forecasting is an important issue for safe and economic operation of power system. However, load data often has strong non-stationarity, nonlinearity and randomness, which increases the difficulty of load forecasting. To improve the prediction accuracy, a hybrid short-term load forecasting method using load feature extraction based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and refined composite multi-scale entropy (RCMSE) and improved bidirectional long short time memory (BiLSTM) error correction is proposed. Firstly, CEEMDAN is used to separate the detailed information and trend information of the original load series, RCMSE is used to reconstruct the feature information, and Spearman is used to screen the features. Secondly, an improved butterfly optimization algorithm (IBOA) is proposed to optimize BiLSTM, and the reconstructed components are predicted respectively. Finally, an error correction model is constructed to mine the hidden information contained in error sequence. The experimental results show that the MAE, MAPE and RMSE of the proposed method are 645 kW, 0.96% and 827.3 kW respectively, and MAPE is improved by about 10% compared with other hybrid models. Therefore, the proposed method can overcome the problem of inaccurate prediction caused by data and inherent defects of models and improve the prediction accuracy.
{"title":"A hybrid short-term load forecasting method using CEEMDAN-RCMSE and improved BiLSTM error correction","authors":"Yi Ning, Meiyu Liu, Xifeng Guo, Zhiyong Liu, Xinlu Wang","doi":"10.3233/jifs-237993","DOIUrl":"https://doi.org/10.3233/jifs-237993","url":null,"abstract":"Accurate load forecasting is an important issue for safe and economic operation of power system. However, load data often has strong non-stationarity, nonlinearity and randomness, which increases the difficulty of load forecasting. To improve the prediction accuracy, a hybrid short-term load forecasting method using load feature extraction based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and refined composite multi-scale entropy (RCMSE) and improved bidirectional long short time memory (BiLSTM) error correction is proposed. Firstly, CEEMDAN is used to separate the detailed information and trend information of the original load series, RCMSE is used to reconstruct the feature information, and Spearman is used to screen the features. Secondly, an improved butterfly optimization algorithm (IBOA) is proposed to optimize BiLSTM, and the reconstructed components are predicted respectively. Finally, an error correction model is constructed to mine the hidden information contained in error sequence. The experimental results show that the MAE, MAPE and RMSE of the proposed method are 645 kW, 0.96% and 827.3 kW respectively, and MAPE is improved by about 10% compared with other hybrid models. Therefore, the proposed method can overcome the problem of inaccurate prediction caused by data and inherent defects of models and improve the prediction accuracy.","PeriodicalId":509313,"journal":{"name":"Journal of Intelligent & Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140228165","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Vinay Kumar Sahu, Dhirendra Pandey, Priyanka Singh, Md Shamsul Haque Ansari, Asif Khan, Naushad Varish, Mohd Waris Khan
The Internet of Things (IoT) strategy enables physical objects to easily produce, receive, and exchange data. IoT devices are getting more common in our daily lives, with diverse applications ranging from consumer sector to industrial and commercial systems. The rapid expansion and widespread use of IoT devices highlight the critical significance of solid and effective cybersecurity standards across the device development life cycle. Therefore, if vulnerability is exploited directly affects the IoT device and the applications. In this paper we investigated and assessed the various real-world critical IoT attacks/vulnerabilities that have affected IoT deployed in the commercial, industrial and consumer sectors since 2010. Subsequently, we evoke the vulnerabilities or type of attack, exploitation techniques, compromised security factors, intensity of vulnerability and impacts of the expounded real-world attacks/vulnerabilities. We first categorise how each attack affects information security parameters, and then we provide a taxonomy based on the security factors that are affected. Next, we perform a risk assessment of the security parameters that are encountered, using two well-known multi-criteria decision-making (MCDM) techniques namely Fuzzy-Analytic Hierarchy Process (F-AHP) and Fuzzy-Analytic Network Process (F-ANP) to determine the severity of severely impacted information security measures.
{"title":"An empirical analysis of evolutionary computing approaches for IoT security assessment","authors":"Vinay Kumar Sahu, Dhirendra Pandey, Priyanka Singh, Md Shamsul Haque Ansari, Asif Khan, Naushad Varish, Mohd Waris Khan","doi":"10.3233/jifs-233759","DOIUrl":"https://doi.org/10.3233/jifs-233759","url":null,"abstract":"The Internet of Things (IoT) strategy enables physical objects to easily produce, receive, and exchange data. IoT devices are getting more common in our daily lives, with diverse applications ranging from consumer sector to industrial and commercial systems. The rapid expansion and widespread use of IoT devices highlight the critical significance of solid and effective cybersecurity standards across the device development life cycle. Therefore, if vulnerability is exploited directly affects the IoT device and the applications. In this paper we investigated and assessed the various real-world critical IoT attacks/vulnerabilities that have affected IoT deployed in the commercial, industrial and consumer sectors since 2010. Subsequently, we evoke the vulnerabilities or type of attack, exploitation techniques, compromised security factors, intensity of vulnerability and impacts of the expounded real-world attacks/vulnerabilities. We first categorise how each attack affects information security parameters, and then we provide a taxonomy based on the security factors that are affected. Next, we perform a risk assessment of the security parameters that are encountered, using two well-known multi-criteria decision-making (MCDM) techniques namely Fuzzy-Analytic Hierarchy Process (F-AHP) and Fuzzy-Analytic Network Process (F-ANP) to determine the severity of severely impacted information security measures.","PeriodicalId":509313,"journal":{"name":"Journal of Intelligent & Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140236391","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Neutrosophic cubic set (NCS) can process complex information by choosing both interval value and single value membership and indeterminacy and falsehood components. The aggregation operators based on Aczel-Alsina t-norm and t-corm are quite effective for evaluating the interrelationship among attributes. The purpose of this paper is to diagnose the interrelationship among attributes with neutrosophic cubic information, and propose a multi-attribute decision-making(MADM) method for supplier selection problem with unknown weight under neutrosophic cubic environment. We defined neutrosophic cubic Aczel-Alsina (NC-AA) operator and neutrosophic cubic Aczel–Alsina weighted arithmetic average (NCAAWAA) operator, then we discussed various important results and some properties of the proposed operators. Additionally, we proposed a MADM method under the presence of the NC-AAWAA operator. When the weights of attributes are unknown, we use the MEREC method to determine the weights. Later, the NC-AAWAA operator and MEREC method are applied to address the supplier selection problem. Finally, a sensitivity analysis and a comparative analysis are conducted to illustrate the stability and superiority of the proposed method. The results show the NC-AAWAA operator can handle the interrelationship among complex information more effectively, and MEREC method can weight the attributes based on the removal effect of a neutrosophic cubic attribute.
{"title":"A novel neutrosophic cubic MADM method based on Aczel-Alsina operator and MEREC and its application for supplier selection","authors":"Shanshan Zhai, Jianping Fan, Lin Liu","doi":"10.3233/jifs-235274","DOIUrl":"https://doi.org/10.3233/jifs-235274","url":null,"abstract":"Neutrosophic cubic set (NCS) can process complex information by choosing both interval value and single value membership and indeterminacy and falsehood components. The aggregation operators based on Aczel-Alsina t-norm and t-corm are quite effective for evaluating the interrelationship among attributes. The purpose of this paper is to diagnose the interrelationship among attributes with neutrosophic cubic information, and propose a multi-attribute decision-making(MADM) method for supplier selection problem with unknown weight under neutrosophic cubic environment. We defined neutrosophic cubic Aczel-Alsina (NC-AA) operator and neutrosophic cubic Aczel–Alsina weighted arithmetic average (NCAAWAA) operator, then we discussed various important results and some properties of the proposed operators. Additionally, we proposed a MADM method under the presence of the NC-AAWAA operator. When the weights of attributes are unknown, we use the MEREC method to determine the weights. Later, the NC-AAWAA operator and MEREC method are applied to address the supplier selection problem. Finally, a sensitivity analysis and a comparative analysis are conducted to illustrate the stability and superiority of the proposed method. The results show the NC-AAWAA operator can handle the interrelationship among complex information more effectively, and MEREC method can weight the attributes based on the removal effect of a neutrosophic cubic attribute.","PeriodicalId":509313,"journal":{"name":"Journal of Intelligent & Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140236971","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xixi Zhao, Liang Gu, Xiaorong Duan, Liguo Wang, Zhenxi Li
Cloud storage attribute libraries usually store a large amount of sensitive data such as personal information and trade secrets. Attackers adopt diverse and complex attack methods to target the cloud storage attribute database, which makes the defense work more challenging. In order to realize the secure storage of information, an attribute based cloud storage anti-attack algorithm based on dynamic authorization access is proposed. According to the characteristic variables of the sample, the data correlation matrix is calculated, and the principal component analysis method is adopted to reduce the dimension of the data, build the anti-attack code model, simulate the dynamic authorization access rights, and calculate the packet loss rate according to the anti-attack flow. Design the initialization stage, cluster stage and cluster center update stage to realize the attack prevention of cloud storage attribute database. The experimental results show that the proposed algorithm can accurately classify the anti-attack code, has good packet processing ability, relatively short page request time, and anti-attack success rate is higher than 90%, which can effectively ensure the stability of the algorithm.
{"title":"Anti-attack algorithm of cloud storage attribute base based on dynamic authorized access","authors":"Xixi Zhao, Liang Gu, Xiaorong Duan, Liguo Wang, Zhenxi Li","doi":"10.3233/jifs-237409","DOIUrl":"https://doi.org/10.3233/jifs-237409","url":null,"abstract":"Cloud storage attribute libraries usually store a large amount of sensitive data such as personal information and trade secrets. Attackers adopt diverse and complex attack methods to target the cloud storage attribute database, which makes the defense work more challenging. In order to realize the secure storage of information, an attribute based cloud storage anti-attack algorithm based on dynamic authorization access is proposed. According to the characteristic variables of the sample, the data correlation matrix is calculated, and the principal component analysis method is adopted to reduce the dimension of the data, build the anti-attack code model, simulate the dynamic authorization access rights, and calculate the packet loss rate according to the anti-attack flow. Design the initialization stage, cluster stage and cluster center update stage to realize the attack prevention of cloud storage attribute database. The experimental results show that the proposed algorithm can accurately classify the anti-attack code, has good packet processing ability, relatively short page request time, and anti-attack success rate is higher than 90%, which can effectively ensure the stability of the algorithm.","PeriodicalId":509313,"journal":{"name":"Journal of Intelligent & Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140237158","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Bin Zhao, Wei Cao, Jiqun Zhang, Yilong Gao, Bin Li, Fengmei Chen
Aiming at the issue that the current click-through rate prediction methods ignore the varying impacts of different input features on prediction accuracy and exhibit low accuracy when dealing with large-scale data, a click-through rate prediction method (GBIFM) which combines Gradient Boosting Decision Tree (GBDT) and Input-aware Factorization Machine (IFM) is proposed in this paper. The proposed GBIFM method employs GBDT for data processing, which can flexibly handle various types of data without the need for one-hot encoding of discrete features. An Input-aware strategy is introduced to refine the weight vector and embedding vector of each feature for different instances, adaptively learning the impact of each input vector on feature representation. Furthermore, a fully connected network is incorporated to capture high-order features in a non-linear manner, enhancing the method’s ability to express and generalize complex structured data. A comprehensive experiment is conducted on the Criteo and Avazu datasets, the results show that compared to typical methods such as DeepFM, AFM, and IFM, the proposed method GBIFM can increase the AUC value by 10% –12% and decrease the Logloss value by 6% –20%, effectively improving the accuracy of click-through rate prediction.
{"title":"Fusion of GBDT and neural network for click-through rate estimation","authors":"Bin Zhao, Wei Cao, Jiqun Zhang, Yilong Gao, Bin Li, Fengmei Chen","doi":"10.3233/jifs-234713","DOIUrl":"https://doi.org/10.3233/jifs-234713","url":null,"abstract":"Aiming at the issue that the current click-through rate prediction methods ignore the varying impacts of different input features on prediction accuracy and exhibit low accuracy when dealing with large-scale data, a click-through rate prediction method (GBIFM) which combines Gradient Boosting Decision Tree (GBDT) and Input-aware Factorization Machine (IFM) is proposed in this paper. The proposed GBIFM method employs GBDT for data processing, which can flexibly handle various types of data without the need for one-hot encoding of discrete features. An Input-aware strategy is introduced to refine the weight vector and embedding vector of each feature for different instances, adaptively learning the impact of each input vector on feature representation. Furthermore, a fully connected network is incorporated to capture high-order features in a non-linear manner, enhancing the method’s ability to express and generalize complex structured data. A comprehensive experiment is conducted on the Criteo and Avazu datasets, the results show that compared to typical methods such as DeepFM, AFM, and IFM, the proposed method GBIFM can increase the AUC value by 10% –12% and decrease the Logloss value by 6% –20%, effectively improving the accuracy of click-through rate prediction.","PeriodicalId":509313,"journal":{"name":"Journal of Intelligent & Fuzzy Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140235959","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：