Pub Date : 2018-11-01DOI: 10.1109/CIS2018.2018.00042
Zhanyuan Yang, Hanfeng Liu, Minping Chen, xia li
Off-topic text detection refers to detecting whether the topic of a text deviates from the required topic. Our work addresses the problem of predicting whether a text is off-topic or not for a given prompt. Prior studies use classical content vector to represent the text and predict it with machine learning based methods. To our knowledge, there are few studies investigated this task using neural networks. In this paper, we propose to use a combination of neural features and surface text features as a representation of a text. Then we input the hidden representation of the text into a softmax layer to get the probability of the prediction. We do several experiments on four datasets. The experimental results show that our method achieves better performance compared with the baseline method.
{"title":"Off-Topic Text Detection Based on Neural Networks Combined with Text Features","authors":"Zhanyuan Yang, Hanfeng Liu, Minping Chen, xia li","doi":"10.1109/CIS2018.2018.00042","DOIUrl":"https://doi.org/10.1109/CIS2018.2018.00042","url":null,"abstract":"Off-topic text detection refers to detecting whether the topic of a text deviates from the required topic. Our work addresses the problem of predicting whether a text is off-topic or not for a given prompt. Prior studies use classical content vector to represent the text and predict it with machine learning based methods. To our knowledge, there are few studies investigated this task using neural networks. In this paper, we propose to use a combination of neural features and surface text features as a representation of a text. Then we input the hidden representation of the text into a softmax layer to get the probability of the prediction. We do several experiments on four datasets. The experimental results show that our method achieves better performance compared with the baseline method.","PeriodicalId":185099,"journal":{"name":"2018 14th International Conference on Computational Intelligence and Security (CIS)","volume":"39 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114102875","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 : 2018-11-01DOI: 10.1109/CIS2018.2018.00108
Jing Nie
This paper first introduces the number of servers faced by higher vocational colleges in the process of informatization construction, the low resource utilization rate, the incompatibility of management systems, and the low degree of management and maintenance automation. The virtualization based on Huawei FusionSphere architecture is proposed. The integrated implementation method performs unified logical division and management of virtual machine resources, shields the physical platform details, and improves the degree of automated management and maintenance of the server.
{"title":"Application of Virtualization Platform in Informationization of Higher Vocational Colleges","authors":"Jing Nie","doi":"10.1109/CIS2018.2018.00108","DOIUrl":"https://doi.org/10.1109/CIS2018.2018.00108","url":null,"abstract":"This paper first introduces the number of servers faced by higher vocational colleges in the process of informatization construction, the low resource utilization rate, the incompatibility of management systems, and the low degree of management and maintenance automation. The virtualization based on Huawei FusionSphere architecture is proposed. The integrated implementation method performs unified logical division and management of virtual machine resources, shields the physical platform details, and improves the degree of automated management and maintenance of the server.","PeriodicalId":185099,"journal":{"name":"2018 14th International Conference on Computational Intelligence and Security (CIS)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115161135","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 : 2018-11-01DOI: 10.1109/CIS2018.2018.00071
Yingle Li, Shuyu Li
In recent years, mobile internet technology and positioning technology have been rapidly developed and widely used, mobile users can enjoy location-based services through mobile smart devices anywhere and anytime. However, they may lead to the leakage of personal sensitive information such as user's spatial temporal location data and so on. Trying to solve this problem and overcoming the shortcoming of traditional randomized dummy generation algorithm, a real-time location privacy protection algorithm based on spatial transform is proposed in the paper, without influencing the quality of user real-time location service. The algorithm uses the number of interest points in the history log file and the road network topology as the key elements of the query context and the motion model, which makes the generated dummy more realistic and effective in both time and space dimension. And the dummy set is encrypted by using the algorithm based on Hilbert space transformation, to make the user query data more secure. The results of experiment show that the algorithm can improve the effectiveness of dummy and gain better obfuscation query result in condition of preserving user privacy information.
{"title":"A Real-Time Location Privacy Protection Method Based on Space Transformation","authors":"Yingle Li, Shuyu Li","doi":"10.1109/CIS2018.2018.00071","DOIUrl":"https://doi.org/10.1109/CIS2018.2018.00071","url":null,"abstract":"In recent years, mobile internet technology and positioning technology have been rapidly developed and widely used, mobile users can enjoy location-based services through mobile smart devices anywhere and anytime. However, they may lead to the leakage of personal sensitive information such as user's spatial temporal location data and so on. Trying to solve this problem and overcoming the shortcoming of traditional randomized dummy generation algorithm, a real-time location privacy protection algorithm based on spatial transform is proposed in the paper, without influencing the quality of user real-time location service. The algorithm uses the number of interest points in the history log file and the road network topology as the key elements of the query context and the motion model, which makes the generated dummy more realistic and effective in both time and space dimension. And the dummy set is encrypted by using the algorithm based on Hilbert space transformation, to make the user query data more secure. The results of experiment show that the algorithm can improve the effectiveness of dummy and gain better obfuscation query result in condition of preserving user privacy information.","PeriodicalId":185099,"journal":{"name":"2018 14th International Conference on Computational Intelligence and Security (CIS)","volume":"47 7","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113981587","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 : 2018-11-01DOI: 10.1109/CIS2018.2018.00009
A. Mehmood, M. Iqbal, H. Dawood, Ping Guo
Modern supercomputers are capable of performing elementary operations of the order of petaflops. This power is comparable with the computational power of a human brain. The power supply required by supercomputers is in megawatts while human brain requires few watts to perform the same elementary operations as the modern supercomputers can. Thus the power consumption of supercomputers can be reduced (about 10 times) by considering the neuromorphic structure of a brain and attempt to mimic it on hardware chip to construct the computer that can function in the same manner as the human brain. In this paper we have proposed to develop the model for single brain cell, that can be replicated to built the whole brain model having computational power of supercomputers but the energy supply comparable with human brain.
{"title":"Computationally Efficient Low Power Neuron Model for Digital Brain","authors":"A. Mehmood, M. Iqbal, H. Dawood, Ping Guo","doi":"10.1109/CIS2018.2018.00009","DOIUrl":"https://doi.org/10.1109/CIS2018.2018.00009","url":null,"abstract":"Modern supercomputers are capable of performing elementary operations of the order of petaflops. This power is comparable with the computational power of a human brain. The power supply required by supercomputers is in megawatts while human brain requires few watts to perform the same elementary operations as the modern supercomputers can. Thus the power consumption of supercomputers can be reduced (about 10 times) by considering the neuromorphic structure of a brain and attempt to mimic it on hardware chip to construct the computer that can function in the same manner as the human brain. In this paper we have proposed to develop the model for single brain cell, that can be replicated to built the whole brain model having computational power of supercomputers but the energy supply comparable with human brain.","PeriodicalId":185099,"journal":{"name":"2018 14th International Conference on Computational Intelligence and Security (CIS)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128570931","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 : 2018-11-01DOI: 10.1109/CIS2018.2018.00060
Liping Chen, Jun Liu, Weitao Ha
Smart grid utilizes cloud service to realize reliable, efficient, secured, and cost-effective power management, but there are a number of security risks in the cloud service of smart grid. The security risks are particularly problematic to operators of power information infrastructure who want to leverage the benefits of cloud. In this paper, security risk of cloud service in the smart grid are categorized and analyzed characteristics, and multi-layered index system of general technical risks is established, which applies to different patterns of cloud service. Cloud service risk of smart grid can evaluate according indexes.
{"title":"Cloud Service Risk in the Smart Grid","authors":"Liping Chen, Jun Liu, Weitao Ha","doi":"10.1109/CIS2018.2018.00060","DOIUrl":"https://doi.org/10.1109/CIS2018.2018.00060","url":null,"abstract":"Smart grid utilizes cloud service to realize reliable, efficient, secured, and cost-effective power management, but there are a number of security risks in the cloud service of smart grid. The security risks are particularly problematic to operators of power information infrastructure who want to leverage the benefits of cloud. In this paper, security risk of cloud service in the smart grid are categorized and analyzed characteristics, and multi-layered index system of general technical risks is established, which applies to different patterns of cloud service. Cloud service risk of smart grid can evaluate according indexes.","PeriodicalId":185099,"journal":{"name":"2018 14th International Conference on Computational Intelligence and Security (CIS)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130058876","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 : 2018-11-01DOI: 10.1109/CIS2018.2018.00052
Fan Ding, Yihong Long, Peili Wu
Secret sharing is commonly used to protect the user's private key. SM2 is an elliptic curve public-key cryptography algorithm released by China's State Cryptography Administration. For its unique digital signature operation, ordinary secret sharing schemes are not suitable for the case of the digital signature using the SM2 private key. To solve this problem, the product-based secret sharing scheme and the summation-based secret sharing scheme for the SM2 digital signature are proposed in this paper. The summation-based secret sharing scheme, in particular, contains ordinary secret sharing and threshold secret sharing. In addition, this work applies the above two schemes to the Android mobile terminal to protect a user's SM2 private key.
{"title":"Study on Secret Sharing for SM2 Digital Signature and Its Application","authors":"Fan Ding, Yihong Long, Peili Wu","doi":"10.1109/CIS2018.2018.00052","DOIUrl":"https://doi.org/10.1109/CIS2018.2018.00052","url":null,"abstract":"Secret sharing is commonly used to protect the user's private key. SM2 is an elliptic curve public-key cryptography algorithm released by China's State Cryptography Administration. For its unique digital signature operation, ordinary secret sharing schemes are not suitable for the case of the digital signature using the SM2 private key. To solve this problem, the product-based secret sharing scheme and the summation-based secret sharing scheme for the SM2 digital signature are proposed in this paper. The summation-based secret sharing scheme, in particular, contains ordinary secret sharing and threshold secret sharing. In addition, this work applies the above two schemes to the Android mobile terminal to protect a user's SM2 private key.","PeriodicalId":185099,"journal":{"name":"2018 14th International Conference on Computational Intelligence and Security (CIS)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121824147","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 : 2018-11-01DOI: 10.1109/CIS2018.2018.00104
Yi Wang, Zhiping Tan
A modified RSA encryption algorithm based on meminductor chaos circuit is proposed in this paper. On the basis of the original RSA encryption algorithm, utilizing meminductor chaotic circuit generate chaos signal conceals the public key in the RSA algorithm, so it can improve information security effectively. Finally, the modified RSA encryption algorithm is used to complete the real-time voice encryption system design based on the chaotic synchronization system. The simulation results are verified by numerical simulations.
{"title":"Modified RSA Encryption Algorithm Based on Chaos and Its Application in Voice Encryption System","authors":"Yi Wang, Zhiping Tan","doi":"10.1109/CIS2018.2018.00104","DOIUrl":"https://doi.org/10.1109/CIS2018.2018.00104","url":null,"abstract":"A modified RSA encryption algorithm based on meminductor chaos circuit is proposed in this paper. On the basis of the original RSA encryption algorithm, utilizing meminductor chaotic circuit generate chaos signal conceals the public key in the RSA algorithm, so it can improve information security effectively. Finally, the modified RSA encryption algorithm is used to complete the real-time voice encryption system design based on the chaotic synchronization system. The simulation results are verified by numerical simulations.","PeriodicalId":185099,"journal":{"name":"2018 14th International Conference on Computational Intelligence and Security (CIS)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126351115","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 : 2018-11-01DOI: 10.1109/CIS2018.2018.00096
Haitao Chen, Wensheng Chen, Binbin Pan, Bo Chen
Nonnegative matrix factorization (NMF) is a promising approach for image-data representation and classification under the nonnegativity constraint. However, the traditional NMF does not exploit the data-label information and its performance will be degraded in classification tasks. To overcome the flaw of NMF, this paper proposes a novel enhanced nonnegative matrix factorization (ENMF) method for learning powerful discriminative feature. The basic idea is that the training data from the same class are forced to embed into their own feature subspaces, where these subspaces are mutually orthogonal. The ENMF update rule is obtained by means of auxiliary function technique and Cardano's formula. We prove and analyze the convergence of the proposed ENMF algorithm theoretically and empirically. Experimental results on face recognition show that the proposed method outperforms the existing state-of-the-art NMF-based algorithms.
{"title":"A Novel Enhanced Nonnegative Feature Extraction Approach","authors":"Haitao Chen, Wensheng Chen, Binbin Pan, Bo Chen","doi":"10.1109/CIS2018.2018.00096","DOIUrl":"https://doi.org/10.1109/CIS2018.2018.00096","url":null,"abstract":"Nonnegative matrix factorization (NMF) is a promising approach for image-data representation and classification under the nonnegativity constraint. However, the traditional NMF does not exploit the data-label information and its performance will be degraded in classification tasks. To overcome the flaw of NMF, this paper proposes a novel enhanced nonnegative matrix factorization (ENMF) method for learning powerful discriminative feature. The basic idea is that the training data from the same class are forced to embed into their own feature subspaces, where these subspaces are mutually orthogonal. The ENMF update rule is obtained by means of auxiliary function technique and Cardano's formula. We prove and analyze the convergence of the proposed ENMF algorithm theoretically and empirically. Experimental results on face recognition show that the proposed method outperforms the existing state-of-the-art NMF-based algorithms.","PeriodicalId":185099,"journal":{"name":"2018 14th International Conference on Computational Intelligence and Security (CIS)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121495506","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 : 2018-11-01DOI: 10.1109/CIS2018.2018.00058
Zhengxin Fu, Sijia Liu, Kun Xia, Bin Yu
Secret image sharing technology is an effective approach to encode the secret image into several shares, and the original image can be recovered by the remaining shares even some shares are lost. As a typical two-dimensional machine reada-ble code, QR code is widely used in human life due to its fast reading speed, high data density and strong error correction capability. Combined with the characteristics of QR code and secret image sharing, an extended secret image sharing scheme was proposed based on QR code, where "extended" means that the generated shares were visually similar to the QR code. The main idea is to control the parameters' selec-tion of polynomial using the binary QR codes. Meanwhile, the average gray difference of the shares was defined as α to measure the similarity between QR-like shares and the origi-nal carrier QR codes. Based on α, a secret sharing algorithm was designed to generate QR-like shares. At last, upper and lower limits of α are introduced through experimental analy-sis, and the relationship between the error correction level of carrier QR code and the lower limit of α.
{"title":"Improved Extended Polynomial-Based Secret Image Sharing Scheme Using QR Code","authors":"Zhengxin Fu, Sijia Liu, Kun Xia, Bin Yu","doi":"10.1109/CIS2018.2018.00058","DOIUrl":"https://doi.org/10.1109/CIS2018.2018.00058","url":null,"abstract":"Secret image sharing technology is an effective approach to encode the secret image into several shares, and the original image can be recovered by the remaining shares even some shares are lost. As a typical two-dimensional machine reada-ble code, QR code is widely used in human life due to its fast reading speed, high data density and strong error correction capability. Combined with the characteristics of QR code and secret image sharing, an extended secret image sharing scheme was proposed based on QR code, where \"extended\" means that the generated shares were visually similar to the QR code. The main idea is to control the parameters' selec-tion of polynomial using the binary QR codes. Meanwhile, the average gray difference of the shares was defined as α to measure the similarity between QR-like shares and the origi-nal carrier QR codes. Based on α, a secret sharing algorithm was designed to generate QR-like shares. At last, upper and lower limits of α are introduced through experimental analy-sis, and the relationship between the error correction level of carrier QR code and the lower limit of α.","PeriodicalId":185099,"journal":{"name":"2018 14th International Conference on Computational Intelligence and Security (CIS)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132635146","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 : 2018-11-01DOI: 10.1109/CIS2018.2018.00015
Zixian Lin, Hai-Lin Liu, Fangqing Gu
In this paper, we propose an evolutionary multi-and many-objective optimization algorithm combining I_SDE + and region decomposition. It decomposes the objective space into a number of sub-regions by a set of direction vectors and independently calculates the indicator I_SDE + by using the corresponding direction vector in each subregion. Thus, the convergence direction of each sub-region is relatively adjusted. In this way, the proposed algorithm can adapt to various of Pareto Front shapes. The inferior individuals are eliminated according to the value of I_SDE + of each individual one by one. In the experiments, we compare the proposed algorithm with four evolutionary multi-and many-objective optimization algorithms on WFG series with different number of objectives. The result shows that the proposed algorithm promotes diversity and convergence.
{"title":"An Evolutionary Multi- and Many-Objective Optimization Algorithm Based on ISDE + and Region Decomposition","authors":"Zixian Lin, Hai-Lin Liu, Fangqing Gu","doi":"10.1109/CIS2018.2018.00015","DOIUrl":"https://doi.org/10.1109/CIS2018.2018.00015","url":null,"abstract":"In this paper, we propose an evolutionary multi-and many-objective optimization algorithm combining I_SDE + and region decomposition. It decomposes the objective space into a number of sub-regions by a set of direction vectors and independently calculates the indicator I_SDE + by using the corresponding direction vector in each subregion. Thus, the convergence direction of each sub-region is relatively adjusted. In this way, the proposed algorithm can adapt to various of Pareto Front shapes. The inferior individuals are eliminated according to the value of I_SDE + of each individual one by one. In the experiments, we compare the proposed algorithm with four evolutionary multi-and many-objective optimization algorithms on WFG series with different number of objectives. The result shows that the proposed algorithm promotes diversity and convergence.","PeriodicalId":185099,"journal":{"name":"2018 14th International Conference on Computational Intelligence and Security (CIS)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133683908","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：