Satyabrata Pradhan, Rajveer Singh, Komal Kachru, S. Narasimhamurthy
We describe an Early Warning System (EWS) which enables the root cause analysis for initiating quality improvements in the manufacturing shop floor and process engineering departments, at product OEMs as well as their tiered suppliers. The EWS combines the use of custom designed domain ontology of manufacturing processes and failure related knowledge, innovative application of domain knowledge in the form of probability constraints and a novel two step constrained optimization approach to causal network construction. Probabilistic reasoning is the main vehicle for inference from the causal network. This inference engine provides the capability to do a root cause analysis in manufacturing scenarios, and is thus a powerful weapon for an automotive EWS. This technique is widely applicable and can be used in various contexts in the broader manufacturing industry as well.
{"title":"A Bayesian Network Based Approach for Root-Cause-Analysis in Manufacturing Process","authors":"Satyabrata Pradhan, Rajveer Singh, Komal Kachru, S. Narasimhamurthy","doi":"10.1109/CIS.2007.214","DOIUrl":"https://doi.org/10.1109/CIS.2007.214","url":null,"abstract":"We describe an Early Warning System (EWS) which enables the root cause analysis for initiating quality improvements in the manufacturing shop floor and process engineering departments, at product OEMs as well as their tiered suppliers. The EWS combines the use of custom designed domain ontology of manufacturing processes and failure related knowledge, innovative application of domain knowledge in the form of probability constraints and a novel two step constrained optimization approach to causal network construction. Probabilistic reasoning is the main vehicle for inference from the causal network. This inference engine provides the capability to do a root cause analysis in manufacturing scenarios, and is thus a powerful weapon for an automotive EWS. This technique is widely applicable and can be used in various contexts in the broader manufacturing industry as well.","PeriodicalId":127238,"journal":{"name":"2007 International Conference on Computational Intelligence and Security (CIS 2007)","volume":"149 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134182313","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}
This paper proposes a hybrid approach for real- time Network Intrusion Detection Systems (NIDS). We adopt Random Forest (RF) for feature selection and Minimax Probability Machine (MPM) for intrusion detection. RF provides the variable importance by numeric values so that the irrelevant features can be eliminated. However, the NIDS based on RF is slow to build intrusion detection model. We employ MPM, since MPM has been shown a better performance, compared with RF in terms of model building time. To validate the feasibility, we carry out several times of experiments with KDD 1999 intrusion detection dataset. The experimental results show the proposed approach is faster and more lightweight than the previous approaches while guaranteeing high detection rates so that it is suitable for real-time NIDS.
{"title":"A Hybrid Approach for Real-Time Network Intrusion Detection Systems","authors":"Jia Li, M. Xie","doi":"10.1109/CIS.2007.10","DOIUrl":"https://doi.org/10.1109/CIS.2007.10","url":null,"abstract":"This paper proposes a hybrid approach for real- time Network Intrusion Detection Systems (NIDS). We adopt Random Forest (RF) for feature selection and Minimax Probability Machine (MPM) for intrusion detection. RF provides the variable importance by numeric values so that the irrelevant features can be eliminated. However, the NIDS based on RF is slow to build intrusion detection model. We employ MPM, since MPM has been shown a better performance, compared with RF in terms of model building time. To validate the feasibility, we carry out several times of experiments with KDD 1999 intrusion detection dataset. The experimental results show the proposed approach is faster and more lightweight than the previous approaches while guaranteeing high detection rates so that it is suitable for real-time NIDS.","PeriodicalId":127238,"journal":{"name":"2007 International Conference on Computational Intelligence and Security (CIS 2007)","volume":"94 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122700595","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}
Biometric technologies have shown much more impor- tance in various application. Among them, iris recognition is considered as one of the most reliable and accurate tech- nologies. As the first step of iris recognition, the location of iris will affect the performance of the whole system. This paper proposes an improved algorithm to locate iris and eyelids. Morphological operation is applied to remove eye- lashes in process of iris boundary location. And optimal step length is calculated to reduce search time. Experimen- tal results demonstrate that the proposed iris location algo- rithm is able to achieve a good performance with accuracy more than 97.6%.
{"title":"An Improved Algorithm for Iris Location","authors":"Xuehu Yan, Shenghong Chen, X. Niu","doi":"10.1109/CIS.2007.98","DOIUrl":"https://doi.org/10.1109/CIS.2007.98","url":null,"abstract":"Biometric technologies have shown much more impor- tance in various application. Among them, iris recognition is considered as one of the most reliable and accurate tech- nologies. As the first step of iris recognition, the location of iris will affect the performance of the whole system. This paper proposes an improved algorithm to locate iris and eyelids. Morphological operation is applied to remove eye- lashes in process of iris boundary location. And optimal step length is calculated to reduce search time. Experimen- tal results demonstrate that the proposed iris location algo- rithm is able to achieve a good performance with accuracy more than 97.6%.","PeriodicalId":127238,"journal":{"name":"2007 International Conference on Computational Intelligence and Security (CIS 2007)","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128415277","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}
This paper proposes a Secure Encrypted-data Aggregation (SEA) scheme in mobile wireless sensor networks (MWSN) environment. Our design for data aggregation eliminates redundant sensor readings without using encryption and maintains data secrecy and privacy during transmission. In contrast to conventional schemes, our proposed scheme provides security and privacy, and duplicate instances of original readings will be aggregated into a single packet; therefore, more energy can be saved.
{"title":"SEA: Secure Encrypted-Data Aggregation in Mobile Wireless Sensor Networks","authors":"Shih-I Huang, S. Shieh","doi":"10.1109/CIS.2007.207","DOIUrl":"https://doi.org/10.1109/CIS.2007.207","url":null,"abstract":"This paper proposes a Secure Encrypted-data Aggregation (SEA) scheme in mobile wireless sensor networks (MWSN) environment. Our design for data aggregation eliminates redundant sensor readings without using encryption and maintains data secrecy and privacy during transmission. In contrast to conventional schemes, our proposed scheme provides security and privacy, and duplicate instances of original readings will be aggregated into a single packet; therefore, more energy can be saved.","PeriodicalId":127238,"journal":{"name":"2007 International Conference on Computational Intelligence and Security (CIS 2007)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116021312","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}
In a generalized (t1/n1-t2/n2) proxy signature scheme with known signers, any t1 or more original signers out of n1 original signers (1 t1 n1) can represent the original group to delegate the signing capability, and t2 or more proxy signers out of n2 proxy signers (1 t2 n2) can represent the proxy group to sign message on behalf of the original group. In the paper, we show that Hwang et al.'s generalized proxy signature scheme is vulnerable to the original signers' forgery attack. After a malicious original group of t1 (t1 t1 n1) signers obtains a proxy sig- nature (Mw, K, AOSID, M, R, S, AP SID), the original signer group can collude to generate a generalized proxy signature without the agreement of the proxy group with the identities AP SID. Hwang et al.'s generalized proxy signa- ture scheme is unable to meet nonrepudiation. We propose an improved generalized proxy signature scheme which can resist our original signer group's collusion attack.
{"title":"Improvement on a Generalized Scheme of Proxy Signature Based on Elliptic Curves","authors":"Zuowen Tan","doi":"10.1109/CIS.2007.78","DOIUrl":"https://doi.org/10.1109/CIS.2007.78","url":null,"abstract":"In a generalized (t1/n1-t2/n2) proxy signature scheme with known signers, any t1 or more original signers out of n1 original signers (1 t1 n1) can represent the original group to delegate the signing capability, and t2 or more proxy signers out of n2 proxy signers (1 t2 n2) can represent the proxy group to sign message on behalf of the original group. In the paper, we show that Hwang et al.'s generalized proxy signature scheme is vulnerable to the original signers' forgery attack. After a malicious original group of t1 (t1 t1 n1) signers obtains a proxy sig- nature (Mw, K, AOSID, M, R, S, AP SID), the original signer group can collude to generate a generalized proxy signature without the agreement of the proxy group with the identities AP SID. Hwang et al.'s generalized proxy signa- ture scheme is unable to meet nonrepudiation. We propose an improved generalized proxy signature scheme which can resist our original signer group's collusion attack.","PeriodicalId":127238,"journal":{"name":"2007 International Conference on Computational Intelligence and Security (CIS 2007)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117296760","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}
Recently semi-supervised learning has been gain a surge of interests, but there is a few of research on semi- supervised learning using geodesic distance. The simplest semi-supervised classification algorithm is geodesic nearest neighbors (GNN). However the naive implementation of GNN algorithm is sensitive to the neighborhood scale parameter and suffers from the dilemma of neighborhood scale parameter selection. In this paper, instead of searching for the best neighborhood parameter, we propose a pruned-GNN, which utilize the non-negative reconstructing coefficients to prune the neighborhood graph in order to facilitate the selection of neighborhood scale parameter. Experimental results on several benchmark databases have shown that the proposed pruned-GNN can produce promising accuracies.
{"title":"Pruning Neighborhood Graph for Geodesic Distance Based Semi-Supervised Classification","authors":"Chun-Guang Li, Jun Guo, Honggang Zhang","doi":"10.1109/CIS.2007.102","DOIUrl":"https://doi.org/10.1109/CIS.2007.102","url":null,"abstract":"Recently semi-supervised learning has been gain a surge of interests, but there is a few of research on semi- supervised learning using geodesic distance. The simplest semi-supervised classification algorithm is geodesic nearest neighbors (GNN). However the naive implementation of GNN algorithm is sensitive to the neighborhood scale parameter and suffers from the dilemma of neighborhood scale parameter selection. In this paper, instead of searching for the best neighborhood parameter, we propose a pruned-GNN, which utilize the non-negative reconstructing coefficients to prune the neighborhood graph in order to facilitate the selection of neighborhood scale parameter. Experimental results on several benchmark databases have shown that the proposed pruned-GNN can produce promising accuracies.","PeriodicalId":127238,"journal":{"name":"2007 International Conference on Computational Intelligence and Security (CIS 2007)","volume":"47 28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115594368","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}
Video surveillance has become more and more prevalent. It is a basic problem to get the number of access people in scenes. When occlusions occur, it becomes difficult to count people. We propose a fast and robust people counting method, and implement a system. In our system, we use group tracking to compensate weakness of multiple human segmentation, which can handle complete occlusion. Our system can run in real-time about 30fps for CIF video, with counting accuracy defined by frame above 95%.
{"title":"A Fast and Robust People Counting Method in Video Surveillance","authors":"Enwei Zhang, Feng Chen","doi":"10.1109/CIS.2007.85","DOIUrl":"https://doi.org/10.1109/CIS.2007.85","url":null,"abstract":"Video surveillance has become more and more prevalent. It is a basic problem to get the number of access people in scenes. When occlusions occur, it becomes difficult to count people. We propose a fast and robust people counting method, and implement a system. In our system, we use group tracking to compensate weakness of multiple human segmentation, which can handle complete occlusion. Our system can run in real-time about 30fps for CIF video, with counting accuracy defined by frame above 95%.","PeriodicalId":127238,"journal":{"name":"2007 International Conference on Computational Intelligence and Security (CIS 2007)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114927178","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}
With the development and application of H.264 standard, the technology of H.264-based video data security becomes increasingly important. This paper proposes a new selective encryption scheme based on H.264, it combines the AES OFB mode with the sign encryption algorithm, and encrypts DCs and parts of ACs respectively. This method not only keeps advantages of former selective encryption algorithms in computational complexity and error-propagation prevention, but also efficiently make up for the deficiency in security and compression performance. Experimental results show that the proposed method exhibits low complexity and good security, and it has little effect on compression ratio and supports error- propagation prevention. Moreover, it is suitable for secure transmission of mobile multimedia and wireless multimedia network based on H.264.
{"title":"Design of a New Selective Video Encryption Scheme Based on H.264","authors":"Yajun Wang, Mian Cai, Feng Tang","doi":"10.1109/CIS.2007.99","DOIUrl":"https://doi.org/10.1109/CIS.2007.99","url":null,"abstract":"With the development and application of H.264 standard, the technology of H.264-based video data security becomes increasingly important. This paper proposes a new selective encryption scheme based on H.264, it combines the AES OFB mode with the sign encryption algorithm, and encrypts DCs and parts of ACs respectively. This method not only keeps advantages of former selective encryption algorithms in computational complexity and error-propagation prevention, but also efficiently make up for the deficiency in security and compression performance. Experimental results show that the proposed method exhibits low complexity and good security, and it has little effect on compression ratio and supports error- propagation prevention. Moreover, it is suitable for secure transmission of mobile multimedia and wireless multimedia network based on H.264.","PeriodicalId":127238,"journal":{"name":"2007 International Conference on Computational Intelligence and Security (CIS 2007)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127600528","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}
Ye Ji, Ting Liu, Lequan Min, Geng Zhao, Xiaohong Qin
In today's large complex organizational network, security is a challenging task for most of the administrators. The typical means by which an attacker breaks into a network is through a series of exploits, where each exploit in the series satisfies the pre-condition for subsequent exploits and makes a causal relationship among them. Such a series of exploits constitutes an attack path and the set of all possible attack paths form an attack graph. Present day vulnerability scanners are able to identify the vulnerabilities in isolation but there is a need for correlation among these vulnerabilities to identify overall risk of the network. In this paper we propose a novel approach by finding out an attack path consisting of logically connected exploits and extends it to an attack graph. The solution also finds out the set of root cause vulnerabilities for overall security threat while taking care the inherent time and scalability problem of attack graph generation.
{"title":"An Artificial Intelligence Based Approach for Risk Management Using Attack Graph","authors":"Ye Ji, Ting Liu, Lequan Min, Geng Zhao, Xiaohong Qin","doi":"10.1109/CIS.2007.145","DOIUrl":"https://doi.org/10.1109/CIS.2007.145","url":null,"abstract":"In today's large complex organizational network, security is a challenging task for most of the administrators. The typical means by which an attacker breaks into a network is through a series of exploits, where each exploit in the series satisfies the pre-condition for subsequent exploits and makes a causal relationship among them. Such a series of exploits constitutes an attack path and the set of all possible attack paths form an attack graph. Present day vulnerability scanners are able to identify the vulnerabilities in isolation but there is a need for correlation among these vulnerabilities to identify overall risk of the network. In this paper we propose a novel approach by finding out an attack path consisting of logically connected exploits and extends it to an attack graph. The solution also finds out the set of root cause vulnerabilities for overall security threat while taking care the inherent time and scalability problem of attack graph generation.","PeriodicalId":127238,"journal":{"name":"2007 International Conference on Computational Intelligence and Security (CIS 2007)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125279517","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}
Level set method is being applied actively in image field due to its mathematical perfection and maturity. In this paper, based on Mumford-Shah model with Level Set method, the finite difference and third order TVD (total variation diminishing) Runge-Kutta schemes are employed for space and time discretization respectively to solve the model equation. The computation of license plate localization shows that better edge detection results from level set method are obtained compared to those from other edge detection methods such as Roberts, Sobel and Canny. This study result is very valuable to edge detection, object localization and tracing. Keywords: level set method; license plate recognition; object localization
{"title":"Level Set Method for License Plate Localization Technology","authors":"Yuwang Yang, Jun Tao, Jing-Yu Yang","doi":"10.1109/CIS.2007.65","DOIUrl":"https://doi.org/10.1109/CIS.2007.65","url":null,"abstract":"Level set method is being applied actively in image field due to its mathematical perfection and maturity. In this paper, based on Mumford-Shah model with Level Set method, the finite difference and third order TVD (total variation diminishing) Runge-Kutta schemes are employed for space and time discretization respectively to solve the model equation. The computation of license plate localization shows that better edge detection results from level set method are obtained compared to those from other edge detection methods such as Roberts, Sobel and Canny. This study result is very valuable to edge detection, object localization and tracing. Keywords: level set method; license plate recognition; object localization","PeriodicalId":127238,"journal":{"name":"2007 International Conference on Computational Intelligence and Security (CIS 2007)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2007-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125371966","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：