Pub Date : 2022-04-21DOI: 10.1109/IEEECONF52377.2022.10013343
Zinuo Yin, Hailong Ma
Intrusion detection is one of the effective methods to prevent network environment from malicious attack. This paper proposes an intrusion detection method based on CS-SDAE to solve the problem of low detection accuracy caused by low traffic feature extraction accuracy and poor robustness in network intrusion detection. Firstly, the structure optimization algorithm of stacked denoising autoencoder (SDAE) is designed based on Cuckoo Search algorithm, and the number of hidden layers and nodes of each layer is optimized by optimizing the detection accuracy of traffic data. Then, the training data are used to train SDAE to minimize the difference between the reconstructed vector of the noisy data and the original input vector, and the characteristics with strong robustness are obtained. Finally, the extracted features are used to train Softmax to build a classifier to detect malicious attacks. Experimental results show that the proposed method can dynamically adjust the structure of SDAE according to the classification task, and the detection accuracy of SDAE is improved by 20.69% compared with traditional SDAE. It has better detection performance.
{"title":"An Intrusion Detection Method Based on CS-SDAE","authors":"Zinuo Yin, Hailong Ma","doi":"10.1109/IEEECONF52377.2022.10013343","DOIUrl":"https://doi.org/10.1109/IEEECONF52377.2022.10013343","url":null,"abstract":"Intrusion detection is one of the effective methods to prevent network environment from malicious attack. This paper proposes an intrusion detection method based on CS-SDAE to solve the problem of low detection accuracy caused by low traffic feature extraction accuracy and poor robustness in network intrusion detection. Firstly, the structure optimization algorithm of stacked denoising autoencoder (SDAE) is designed based on Cuckoo Search algorithm, and the number of hidden layers and nodes of each layer is optimized by optimizing the detection accuracy of traffic data. Then, the training data are used to train SDAE to minimize the difference between the reconstructed vector of the noisy data and the original input vector, and the characteristics with strong robustness are obtained. Finally, the extracted features are used to train Softmax to build a classifier to detect malicious attacks. Experimental results show that the proposed method can dynamically adjust the structure of SDAE according to the classification task, and the detection accuracy of SDAE is improved by 20.69% compared with traditional SDAE. It has better detection performance.","PeriodicalId":193681,"journal":{"name":"2021 International Conference on Advanced Computing and Endogenous Security","volume":"67 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120896251","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}
Pub Date : 2022-04-21DOI: 10.1109/IEEECONF52377.2022.10013328
Tianliang Lei, Lixin Ji, Shuxin Liu
The development and popularization of Internet technology has stimulated the growth of users' network demands. A large number of users will choose many different social networks to provide users with rich content and services. Cross-social network user identification can help improve user information, provide personalized service recommendations and data mining. This article firstly introduces the cross-social network user identification technology that can identify accounts belonging to the same user on different networks through user attributes, user posted content, user behavior, and network topology relationship models. Secondly, it introduces similarity calculation method of user identification technology, various algorithm performance indicators, and some recent datasets. Finally, the article points out the future research directions of cross-social network user identification technology, which should focus on the weight distribution of user attribute information, multi-dimensional data identification, and large-scale user identification.
{"title":"Investigation of Cross-Social Network User Identification","authors":"Tianliang Lei, Lixin Ji, Shuxin Liu","doi":"10.1109/IEEECONF52377.2022.10013328","DOIUrl":"https://doi.org/10.1109/IEEECONF52377.2022.10013328","url":null,"abstract":"The development and popularization of Internet technology has stimulated the growth of users' network demands. A large number of users will choose many different social networks to provide users with rich content and services. Cross-social network user identification can help improve user information, provide personalized service recommendations and data mining. This article firstly introduces the cross-social network user identification technology that can identify accounts belonging to the same user on different networks through user attributes, user posted content, user behavior, and network topology relationship models. Secondly, it introduces similarity calculation method of user identification technology, various algorithm performance indicators, and some recent datasets. Finally, the article points out the future research directions of cross-social network user identification technology, which should focus on the weight distribution of user attribute information, multi-dimensional data identification, and large-scale user identification.","PeriodicalId":193681,"journal":{"name":"2021 International Conference on Advanced Computing and Endogenous Security","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115923525","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}
As a basic task for computer vision, face detection plays an important role in the application of face recognition. However, in real-world applications, masked face detection is still a challenging problem. In this paper, we present a novel face detection framework for masked faces. Firstly, we use the anchor-level attention mechanism to reduce the impact of complex environments and occlusion on face detection. We select the ground truth with the minims attention loss to supervise the attention layer. Besides, we depart the face features and each part corresponds to the different channel of the feature vector. By the means, the occlusions on the face can be restricted in the local part of the features. The experimental results illustrate that our model improves the accuracy of the face detection task, especially in the masked face detection. Compared to SSH, the average precision of our model has an average of 2.1%, 2.1% and 5.4% improvements on WIDER FACE easy, normal and hard validation datasets, respectively, and an average of 1.6% improvement compared to FAN on MAFA dataset.
{"title":"Masked Face Detection with Anchor-level Attention and Local Feature","authors":"Hongquan Wei, Jianpeng Zhang, Xu-dong Wang, Wenqi Ren","doi":"10.1109/IEEECONF52377.2022.10013105","DOIUrl":"https://doi.org/10.1109/IEEECONF52377.2022.10013105","url":null,"abstract":"As a basic task for computer vision, face detection plays an important role in the application of face recognition. However, in real-world applications, masked face detection is still a challenging problem. In this paper, we present a novel face detection framework for masked faces. Firstly, we use the anchor-level attention mechanism to reduce the impact of complex environments and occlusion on face detection. We select the ground truth with the minims attention loss to supervise the attention layer. Besides, we depart the face features and each part corresponds to the different channel of the feature vector. By the means, the occlusions on the face can be restricted in the local part of the features. The experimental results illustrate that our model improves the accuracy of the face detection task, especially in the masked face detection. Compared to SSH, the average precision of our model has an average of 2.1%, 2.1% and 5.4% improvements on WIDER FACE easy, normal and hard validation datasets, respectively, and an average of 1.6% improvement compared to FAN on MAFA dataset.","PeriodicalId":193681,"journal":{"name":"2021 International Conference on Advanced Computing and Endogenous Security","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129846079","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：