Packet filtering in firewall either accepts or denies network packets based upon a set of pre-defined filters called firewall policy. Firewall policy is designed under the instruction of security policy. A network security policy is a generic document that outlines the needs for computer network access permissions. And it determines how firewall filters are designed. If inconsistencies, such as redundant filters, insufficient filters or contradict filters, exist between security policy and firewall policy, firewall policy could not filter packets exactly, and the network protected by the firewall will be affected. To resolve this problem, we propose an inconsistency detection system to detect the inconsistencies between the security policy and firewall policy. When the administrator could not get host IP addresses, port number and other specific values, according to the network configurations, our proposed system could transform the network security policy and firewall policy to the same range value, represent and analyze their spatial relationships to detect their inconsistencies. The proposed system has been successfully implemented in a prototype system. We have been confirmed the effectiveness of the proposed system.
{"title":"Inconsistency Detection System for Security Policy and Firewall Policy","authors":"Yi Yin, Xiaodong Xu, Y. Katayama, N. Takahashi","doi":"10.1109/IC-NC.2010.45","DOIUrl":"https://doi.org/10.1109/IC-NC.2010.45","url":null,"abstract":"Packet filtering in firewall either accepts or denies network packets based upon a set of pre-defined filters called firewall policy. Firewall policy is designed under the instruction of security policy. A network security policy is a generic document that outlines the needs for computer network access permissions. And it determines how firewall filters are designed. If inconsistencies, such as redundant filters, insufficient filters or contradict filters, exist between security policy and firewall policy, firewall policy could not filter packets exactly, and the network protected by the firewall will be affected. To resolve this problem, we propose an inconsistency detection system to detect the inconsistencies between the security policy and firewall policy. When the administrator could not get host IP addresses, port number and other specific values, according to the network configurations, our proposed system could transform the network security policy and firewall policy to the same range value, represent and analyze their spatial relationships to detect their inconsistencies. The proposed system has been successfully implemented in a prototype system. We have been confirmed the effectiveness of the proposed system.","PeriodicalId":375145,"journal":{"name":"2010 First International Conference on Networking and Computing","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123965026","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}
A Modified Hierarchical 3D-Torus (MH3DT) network is a 3D-torus network of multiple basic modules, in which the basic modules are themselves 3D-torus networks which are hierarchically interconnected into higher-level networks. The static network performance of the MH3DT has already been studied and has been shown to be good. Dynamic communication performance has been evaluated using dimension-order routing and 2 virtual channels under uniform traffic patterns but not under non-uniform traffic patterns. In this paper, we evaluate the dynamic communication performance of MH3DT under five non-uniform traffic patterns, and compare it with other networks. We found that under non-uniform traffic patterns, the MH3DT yields high throughput and low latency, providing better dynamic communication performance compared to H3DT, TESH, mesh, and torus networks. Also, we found that non-uniform traffic patterns have higher throughput than uniform traffic patterns in the MH3DT network.
{"title":"Dynamic Communication Performance of a Modified Hierarchical 3D-Torus Network under Non-uniform Traffic Patterns","authors":"M. Rahman, Yukinori Sato, Y. Inoguchi","doi":"10.1109/IC-NC.2010.27","DOIUrl":"https://doi.org/10.1109/IC-NC.2010.27","url":null,"abstract":"A Modified Hierarchical 3D-Torus (MH3DT) network is a 3D-torus network of multiple basic modules, in which the basic modules are themselves 3D-torus networks which are hierarchically interconnected into higher-level networks. The static network performance of the MH3DT has already been studied and has been shown to be good. Dynamic communication performance has been evaluated using dimension-order routing and 2 virtual channels under uniform traffic patterns but not under non-uniform traffic patterns. In this paper, we evaluate the dynamic communication performance of MH3DT under five non-uniform traffic patterns, and compare it with other networks. We found that under non-uniform traffic patterns, the MH3DT yields high throughput and low latency, providing better dynamic communication performance compared to H3DT, TESH, mesh, and torus networks. Also, we found that non-uniform traffic patterns have higher throughput than uniform traffic patterns in the MH3DT network.","PeriodicalId":375145,"journal":{"name":"2010 First International Conference on Networking and Computing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129379911","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}
Pulung Waskito, Shinobu Miwa, Y. Mitsukura, H. Nakajo
In this paper, we show parallel implementation of Hilbert-Huang Transform on GPU. This implementation focused on the reducing the computation complexity from O(N) on a single CPU to O(N/P log (N)) on GPU, as well as the use of 'shared-global' switching method to increase performance. Evaluation results show our single GPU implementation using Tesla C1060 achieves 29.0x speedup in best case, and a total of 7.1x speedup for all results when compared to a single Intel dual core CPU.
{"title":"Parallelizing Hilbert-Huang Transform on a GPU","authors":"Pulung Waskito, Shinobu Miwa, Y. Mitsukura, H. Nakajo","doi":"10.1109/IC-NC.2010.44","DOIUrl":"https://doi.org/10.1109/IC-NC.2010.44","url":null,"abstract":"In this paper, we show parallel implementation of Hilbert-Huang Transform on GPU. This implementation focused on the reducing the computation complexity from O(N) on a single CPU to O(N/P log (N)) on GPU, as well as the use of 'shared-global' switching method to increase performance. Evaluation results show our single GPU implementation using Tesla C1060 achieves 29.0x speedup in best case, and a total of 7.1x speedup for all results when compared to a single Intel dual core CPU.","PeriodicalId":375145,"journal":{"name":"2010 First International Conference on Networking and Computing","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129577647","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 this paper, we improve the accuracy of item-based collaborative filtering by introducing a loss compensation based on the TF-IDF weight. The proposed scheme is implemented as a part of a feed reader, and is evaluated through the feedback from users.
{"title":"Article Recommender for Feed Readers with a Loss Compensation Based on the TF-IDF Weight","authors":"Daichi Yokota, S. Fujita","doi":"10.1109/IC-NC.2010.21","DOIUrl":"https://doi.org/10.1109/IC-NC.2010.21","url":null,"abstract":"In this paper, we improve the accuracy of item-based collaborative filtering by introducing a loss compensation based on the TF-IDF weight. The proposed scheme is implemented as a part of a feed reader, and is evaluated through the feedback from users.","PeriodicalId":375145,"journal":{"name":"2010 First International Conference on Networking and Computing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129190204","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}
The objective of Peer-to-Peer Content Delivery Networks is to deliver copyrighted contents to paid clients in an efficient and secure manner. To protect such contents from being distributed to unauthorized peers, Lou and Hwang proposed a proactive content poisoning scheme to restrain an illegal download conducted by unauthorized peers, and a scheme to identify colluders who illegally leak the contents to such unauthorized peers. In this paper, we propose three schemes which extend the Lou and Hwang's colluder detection scheme in two directions. The first idea is to introduce an intensive probing to the check of suspected peers, and the second idea is to adopt a reputation system to select reliable (non-colluder) peers as a decoy. The performance of the resulting scheme is evaluated by simulation. The result of simulations indicates that the proposed schemes detect colluders 30% earlier in average than the original scheme while keeping the accuracy of the colluder detection at medium collusion rate.
{"title":"A Quick Detection of Colluders in P2P CDNs to Avoid an Illegal Leak of the Contents","authors":"E. Abdullah, S. Fujita","doi":"10.1109/IC-NC.2010.14","DOIUrl":"https://doi.org/10.1109/IC-NC.2010.14","url":null,"abstract":"The objective of Peer-to-Peer Content Delivery Networks is to deliver copyrighted contents to paid clients in an efficient and secure manner. To protect such contents from being distributed to unauthorized peers, Lou and Hwang proposed a proactive content poisoning scheme to restrain an illegal download conducted by unauthorized peers, and a scheme to identify colluders who illegally leak the contents to such unauthorized peers. In this paper, we propose three schemes which extend the Lou and Hwang's colluder detection scheme in two directions. The first idea is to introduce an intensive probing to the check of suspected peers, and the second idea is to adopt a reputation system to select reliable (non-colluder) peers as a decoy. The performance of the resulting scheme is evaluated by simulation. The result of simulations indicates that the proposed schemes detect colluders 30% earlier in average than the original scheme while keeping the accuracy of the colluder detection at medium collusion rate.","PeriodicalId":375145,"journal":{"name":"2010 First International Conference on Networking and Computing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130123564","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 this paper, we consider Peer-to-Peer Video on- Demand (P2P VoD) systems based on the Bit Torrent file sharing protocol. Since the rarest first policy adopted in the Bit Torrent protocol could not collect all pieces corresponding to a video file by their playback time, we need to develop a new piece selection rule particularly designed for P2P VoDs. In the proposed scheme, we assume the existence of a media server which can upload any piece upon request, and try to bound the load of such media server by carefully discriminating pieces to be requested, by taking into account the rareness of the pieces held by its nearby peers, estimated size of the overlay network, and the file size to be downloaded. The performance of the proposed scheme is evaluated by simulation.
{"title":"Adaptive Prefetching Scheme for Peer-to-Peer Video-on-Demand Systems with a Media Server","authors":"Ryusuke Uedera, S. Fujita","doi":"10.1109/IC-NC.2010.22","DOIUrl":"https://doi.org/10.1109/IC-NC.2010.22","url":null,"abstract":"In this paper, we consider Peer-to-Peer Video on- Demand (P2P VoD) systems based on the Bit Torrent file sharing protocol. Since the rarest first policy adopted in the Bit Torrent protocol could not collect all pieces corresponding to a video file by their playback time, we need to develop a new piece selection rule particularly designed for P2P VoDs. In the proposed scheme, we assume the existence of a media server which can upload any piece upon request, and try to bound the load of such media server by carefully discriminating pieces to be requested, by taking into account the rareness of the pieces held by its nearby peers, estimated size of the overlay network, and the file size to be downloaded. The performance of the proposed scheme is evaluated by simulation.","PeriodicalId":375145,"journal":{"name":"2010 First International Conference on Networking and Computing","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114967291","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}
The k-edge-connectivity augmentation problem with multipartition constraints (kECAM for short) is defined by “Given an undirected graph G = (V, E) and a multipartition π = {V1,..., Vr} of V with Vi ∩ Vj = ∅ for ∀i, j ∈ {1,..., r} (i ≠ j), find an edge set E' of minimum cardinality, consisting of edges that connect distinct members of π, such that G' = (V, E∪E') is k edge-connected.” In this paper, we propose a parallel algorithm, running on an EREW PRAM, for finding a solution to 2ECAM when G is connected. The main idea is to reduce 2ECAM to the bipartition case, that is, 2ECAM with r = 2.
具有多分区约束的k边连通性增强问题(简称kECAM)定义为“给定一个无向图G = (V, E)和一个多分区π = {V1，…， Vr} of V with Vi∩Vj =∅for∀i, j∈{1，…， r} (i≠j)，求一个最小cardinality的边集E'，它由连接π的不同元素的边组成，使得G' = (V, E∪E')是k边连通的。在本文中，我们提出了一个并行算法，运行在EREW PRAM上，用于寻找G连接时2ECAM的解。主要思想是将2ECAM约简为两分区情况，即r = 2的2ECAM。
{"title":"A Parallel Algorithm for 2-Edge-Connectivity Augmentation of a Connected Graph with Multipartition Constraints","authors":"T. Oki, S. Taoka, Toshimasa Watanabe","doi":"10.1109/IC-NC.2010.58","DOIUrl":"https://doi.org/10.1109/IC-NC.2010.58","url":null,"abstract":"The k-edge-connectivity augmentation problem with multipartition constraints (kECAM for short) is defined by “Given an undirected graph G = (V, E) and a multipartition π = {V1,..., Vr} of V with Vi ∩ Vj = ∅ for ∀i, j ∈ {1,..., r} (i ≠ j), find an edge set E' of minimum cardinality, consisting of edges that connect distinct members of π, such that G' = (V, E∪E') is k edge-connected.” In this paper, we propose a parallel algorithm, running on an EREW PRAM, for finding a solution to 2ECAM when G is connected. The main idea is to reduce 2ECAM to the bipartition case, that is, 2ECAM with r = 2.","PeriodicalId":375145,"journal":{"name":"2010 First International Conference on Networking and Computing","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134281709","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}
T. Koide, R. Kimura, T. Sugahara, K. Okazaki, H. Mattausch
We report a two-dimensional (2D) pixel block scanning architecture for image segmentation by segment growing. This architecture can optimize processing speed, power consumption, and circuit area by modifying size and shape of the pixel block. Real-time processing can be maintained by using additional the two important techniques of (i) boundary-scan of the grown segment only, (ii) continued block-internal segment growing. We analyze and optimize the size and shape trade-offs for the pixel block, and evaluate the proposed architecture by an FPGA. Altogether, the investigated architecture concepts reduce the area-time product by 52.3 % in comparison to a previously reported one-dimensional (1D) scanning architecture.
{"title":"Architecture and FPGA-Implementation of Scalable Picture Segmentation by 2D Scanning with Flexible Pixel-Block Size","authors":"T. Koide, R. Kimura, T. Sugahara, K. Okazaki, H. Mattausch","doi":"10.1109/IC-NC.2010.48","DOIUrl":"https://doi.org/10.1109/IC-NC.2010.48","url":null,"abstract":"We report a two-dimensional (2D) pixel block scanning architecture for image segmentation by segment growing. This architecture can optimize processing speed, power consumption, and circuit area by modifying size and shape of the pixel block. Real-time processing can be maintained by using additional the two important techniques of (i) boundary-scan of the grown segment only, (ii) continued block-internal segment growing. We analyze and optimize the size and shape trade-offs for the pixel block, and evaluate the proposed architecture by an FPGA. Altogether, the investigated architecture concepts reduce the area-time product by 52.3 % in comparison to a previously reported one-dimensional (1D) scanning architecture.","PeriodicalId":375145,"journal":{"name":"2010 First International Conference on Networking and Computing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134283368","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 this paper, we propose a new scheme for packet-switched bufferless Networks-on-Chip (NoCs). The goal is to reduce the area and power consumption while providing high performance. In the proposed scheme, we develop a new bufferless routing algorithm. Extensive cycle-accurate simulations have been conducted to show that the proposed scheme delivers a superior performance compared to both traditional buffered and bufferless methods.
{"title":"Express Circuit Switching: Improving the Performance of Bufferless Networks-on-Chip","authors":"Jing Lin, X. Lin","doi":"10.1109/IC-NC.2010.12","DOIUrl":"https://doi.org/10.1109/IC-NC.2010.12","url":null,"abstract":"In this paper, we propose a new scheme for packet-switched bufferless Networks-on-Chip (NoCs). The goal is to reduce the area and power consumption while providing high performance. In the proposed scheme, we develop a new bufferless routing algorithm. Extensive cycle-accurate simulations have been conducted to show that the proposed scheme delivers a superior performance compared to both traditional buffered and bufferless methods.","PeriodicalId":375145,"journal":{"name":"2010 First International Conference on Networking and Computing","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134554151","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 this paper we propose CUDA-based implementations of two 3D point sets registration algorithms: Soft assign and EM-ICP. Both algorithms are known for being time demanding, even on modern multi-core CPUs. Our GPUbased implementations vastly outperform CPU ones. For instance, our CUDA EM-ICP aligns 5000 points in less than 7 seconds on a GeForce 8800GT, while the same implementation in OpenMP on an Intel Core 2 Quad would take 7 minutes.
{"title":"Softassign and EM-ICP on GPU","authors":"Toru Tamaki, Miho Abe, B. Raytchev, K. Kaneda","doi":"10.1109/IC-NC.2010.60","DOIUrl":"https://doi.org/10.1109/IC-NC.2010.60","url":null,"abstract":"In this paper we propose CUDA-based implementations of two 3D point sets registration algorithms: Soft assign and EM-ICP. Both algorithms are known for being time demanding, even on modern multi-core CPUs. Our GPUbased implementations vastly outperform CPU ones. For instance, our CUDA EM-ICP aligns 5000 points in less than 7 seconds on a GeForce 8800GT, while the same implementation in OpenMP on an Intel Core 2 Quad would take 7 minutes.","PeriodicalId":375145,"journal":{"name":"2010 First International Conference on Networking and Computing","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115423388","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：