2021 Ninth International Symposium on Computing and Networking (CANDAR)最新文献

{"title":"Efficient Final Exponentiation for Pairings on Several Curves Resistant to Special TNFS","authors":"Yuki Nanjo, Masaaki Shirase, Yuta Kodera, Takuya Kusaka, Y. Nogami","doi":"10.1109/CANDAR53791.2021.00014","DOIUrl":"https://doi.org/10.1109/CANDAR53791.2021.00014","url":null,"abstract":"Pairings on elliptic curves are exploited for pairing-based cryptography, e.g., ID-based encryption and group signature authentication. For secure cryptography, it is important to choose the curves that have resistance to a special variant of the tower number field sieve (TNFS) that is an attack for the finite fields. However, for the pairings on several curves with embedding degree $k={10,11,13,14}$ resistant to the special TNFS, efficient algorithms for computing the final exponentiation constructed by the lattice-based method have not been provided. For these curves, the authors present efficient algorithms with the calculation costs in this manuscript.","PeriodicalId":263773,"journal":{"name":"2021 Ninth International Symposium on Computing and Networking (CANDAR)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116804964","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}

{"title":"[Copyright notice]","authors":"","doi":"10.1109/candar53791.2021.00003","DOIUrl":"https://doi.org/10.1109/candar53791.2021.00003","url":null,"abstract":"","PeriodicalId":263773,"journal":{"name":"2021 Ninth International Symposium on Computing and Networking (CANDAR)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117116441","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}

{"title":"Area-efficient Binary and Ternary CNN Accelerator using Random-forest-based Approximation","authors":"Kaisei Kimura, Shota Yatabe, Sora Isobe, Yoichi Tomioka, H. Saito, Y. Kohira, Qiangfu Zhao","doi":"10.1109/CANDAR53791.2021.00023","DOIUrl":"https://doi.org/10.1109/CANDAR53791.2021.00023","url":null,"abstract":"In recent years, the demand for faster inference of convolutional neural networks with a smaller and low-power accelerator is increasing to realize low-latency control of robots and reduce network load. In this paper, we propose a random-forest-based approximation layer unit (RFA-LU) for binary and ternary CNNs to realize faster inference. This unit introduces a novel technique predicting output feature maps using random forest models instead of directly calculating multiply-accumulate (MAC) operations. We demonstrate that the proposed RFA-LU can reduce the number of adaptive logic modules (ALMs) by 56.2% (61.3%) and the number of registers by 85.3% (84.9%) compared with conventional binary (ternary) CNN circuits of the same performance on an Intel Cyclone V SX FPGA.","PeriodicalId":263773,"journal":{"name":"2021 Ninth International Symposium on Computing and Networking (CANDAR)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127593733","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}

{"title":"Low-Latency High-Bandwidth Interconnection Networks by Selective Packet Compression","authors":"Naoya Niwa, H. Amano, M. Koibuchi","doi":"10.1109/CANDAR53791.2021.00015","DOIUrl":"https://doi.org/10.1109/CANDAR53791.2021.00015","url":null,"abstract":"Interconnection network ideally transfers the maximum amount of communication dataset within the least amount of time to fully exploit the parallelism of target applications on parallel computer systems. To this goal, we propose a selective data-compression interconnection network. Data compression virtually increases the effective network bandwidth, while each compute node introduces additional latency overhead to perform (de-)compression operation to end-to-end communication latency. To minimize the effect of the compression latency overhead on the end-to-end communication latency, we selectively apply a compression technique to a packet. The compression operation is taken for long packets and is also taken when network congestion is detected at a network interface. Evaluation results show that simple lossless and lossy compression algorithms have up to 3.0 and 1.8 compression ratios for integer and floating-point communication data in some parallel applications, respectively, while the lossy compression algorithm successfully satisfies the required quality of results. Through a cycle-network simulation, the selective compression method using the above compression algorithms improves by up to 46% the network throughput with the moderate increase of the communication latency of short packets.","PeriodicalId":263773,"journal":{"name":"2021 Ninth International Symposium on Computing and Networking (CANDAR)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133521662","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}

{"title":"Semi-Uniform Deployment of Mobile Robots in Perfect $ell$ -ary Trees","authors":"M. Shibata, S. Tixeuil","doi":"10.1109/CANDAR53791.2021.00031","DOIUrl":"https://doi.org/10.1109/CANDAR53791.2021.00031","url":null,"abstract":"In this paper, we consider the problem of semi-uniform deployment for mobile robots in perfect $ell$-ary trees, where every intermediate node has $ell$ children, and all leaf nodes have the same depth. This problem requires robots to spread in the tree so that, for some positive integer $d$ and some fixed integer $s(0leq sleq d-1)$, each node of depth $s+dj (jgeq 0)$ is occupied by a robot. In other words, after semi-uniform deployment is achieved, nodes of depth $s, s+d, s+2d, ldots$ are occupied by a robot. Robots have an infinite visibility range but are opaque, that is, robot $r_{i}$ cannot observe some robot $r_{j}$ if there exists another robot $r_{k}$ in the path between $r_{i}$ and $r_{j}$. In addition, each robot can emit a light color visible to itself and other robots, taken from a set of $kappa$ colors, at each time step. Then, we clarify the relationship between the number of available light colors and the solvability of the semi-uniform deployment problem. First, we consider robots with the minimum number of available light colors, that is, robots with $kappa =1$ (in this case, robots are oblivious). In this setting, we show that there is no collision-free algorithm to solve the semi-uniform deployment problem with explicit termination. Next, we relax the number of available light colors, that is, we consider robots with $kappa=2$. In this setting, we propose a collision-free algorithm that can solve the problem with explicit termination. Thus, our algorithm is optimal with respect to the number of light colors. In addition, to the best of our knowledge, this paper is the first to report research considering (a variant of) uniform deployment in graphs other than rings or grids.","PeriodicalId":263773,"journal":{"name":"2021 Ninth International Symposium on Computing and Networking (CANDAR)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115003086","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}

{"title":"Accelerate CNN Models via Filter Pruning and Sparse Tensor Core","authors":"andXurong Chen, Pangfeng Liu, Ding-Yong Hong, Jan-Jan Wu","doi":"10.1109/CANDAR53791.2021.00009","DOIUrl":"https://doi.org/10.1109/CANDAR53791.2021.00009","url":null,"abstract":"Convolutional neural network (CNN) is a state-of-the-art technique in machine learning and has achieved high accuracy in many computer vision tasks. However, the number of the parameters of the models is fast increasing for accuracy improvement; therefore, it requires more computation time and memory space for training and inference. Thus, compressing the model size and improving the inference speed has become an important issue. This paper focuses on filter pruning and NVIDIA sparse tensor core. Filter pruning is one of the model compression methods which uses a method that evaluates the importance of filters in the CNN model and removes the less important ones. NVIDIA sparse tensor core is the hardware support provided by NVIDIA Ampere GPU architecture. The sparse tensor core can speed up the matrix multiplication if the matrix has a structure that manifests as a 2:4 pattern. In this paper, we proposed a hybrid pruning metric to prune the CNN model. The hybrid pruning combines filter pruning and 2:4 pruning. We apply filter pruning to remove the redundant filters in convolutional layers to make the model smaller. Next, we use 2:4 pruning to prune the model according to a 2:4 pattern to utilize the sparse tensor core hardware for speedup. In this hybrid pruning situation, we have also proposed a hybrid ranking metric to decide the filter's importance during filter pruning. In hybrid ranking metric, we will preserve the filters that are important for both of the pruning steps. By considering both metrics, we can achieve higher accuracy than traditional filter prunings. We test our hybrid pruning algorithm on MNIST, SVHN, CIFAR-10 datasets using AlexNet. From our experiments, we concluded that our hybrid ranking method achieves better accuracy than the classic L1-norm metric and the output L1-norm metric. When we prune away 40 percent of filters in the model, our method has 2.8 %, 2.9 %, 2.7% higher accuracy than the classic L1-norm metric and the output L1-norm metric on these three datasets. Next, we evaluate the inference speed. We compare the hybrid pruning model with the models that result from either filter pruning or 2:4 pruning. We find that a hybrid pruning model can be 1.3x faster than the filter pruning model with similar accuracy.","PeriodicalId":263773,"journal":{"name":"2021 Ninth International Symposium on Computing and Networking (CANDAR)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129892173","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}

{"title":"CANDAR 2021 Reviewers","authors":"","doi":"10.1109/candar53791.2021.00008","DOIUrl":"https://doi.org/10.1109/candar53791.2021.00008","url":null,"abstract":"","PeriodicalId":263773,"journal":{"name":"2021 Ninth International Symposium on Computing and Networking (CANDAR)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116776992","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}

{"title":"Trajectory Anonymization through Laplace Noise Addition in Latent Space","authors":"Yuiko Sakuma, Thai P. Tran, Tomomu Iwai, Akihito Nishikawa, Hiroaki Nishi","doi":"10.1109/CANDAR53791.2021.00016","DOIUrl":"https://doi.org/10.1109/CANDAR53791.2021.00016","url":null,"abstract":"In recent years, the volume of captured location-based movement data has drastically increased with the prevalence of smartphones. Mobility data are commonly used for smart assistant and personalized advertising applications. However, such data contain considerable sensitive information; thus, they must be anonymized before they can be published or analyzed. In this study, we investigate the problem of anonymization for trajectory publication. Anonymizing trajectories is challenging because they have high dimensionality in both the spatial and temporal domains. Traditional anonymization methods cannot handle high dimensionality without significantly sacrificing data utility. The proposed method addresses this limitation by training a Seq2Seq autoencoder model to reconstruct trajectories from the spatiotemporal input, followed by distributing the Laplace noise to the principal components of the Seq2Seq encoder's hidden-layer output under differential privacy. By distributing the privacy budget in the latent space, the proposed method can output trajectories that satisfy differential privacy while maintaining embedded information. Experimental results from the application of the proposed method to real-life movement trajectory data from Saitama, Japan, demonstrate a reduction in data loss by up to 75.7 % while maintaining significant data utility.","PeriodicalId":263773,"journal":{"name":"2021 Ninth International Symposium on Computing and Networking (CANDAR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129244521","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}

{"title":"On the Performance of Hidden Markov Model Spectrum Opportunity Forecast on Limited Observed Channel Activity","authors":"Rodrigo F. Bezerra, J. Bordim, M. V. Lamar, Marcos F. Caetano","doi":"10.1109/CANDAR53791.2021.00018","DOIUrl":"https://doi.org/10.1109/CANDAR53791.2021.00018","url":null,"abstract":"The increasing demands for wireless channels to accommodate the surge of internet of things devices and the associated services exacerbated the need for flexible channel allocation strategies. Opportunistic spectrum sharing is expected to provide a more reasonable use of the limited radio frequencies available by allowing the coexistence of licensed users and unlicensed users in the same frequency. This arrangement is called opportunistic channel allocation, where unlicensed users explore the channel when the licensed user is not transmitting. The challenge in opportunistic spectrum allocation is to find transmission opportunities. Accurate opportunity detection mechanisms to avoid interference and improve spectrum usage are highly desirable. Hidden Markov Model training and predicting procedures are proposed in this work to balance the number of training sequences to limit the influence of outliers and provide opportunity forecast even when the training process is executed over a limited number of observed sequences. Our findings show that higher accuracy can be obtained even when the HMM is trained with a reduced number of transmission sequences. The results show that, compared to similar works, the proposed alternatives reduce collision rates while improving the overall number of seized transmission opportunities. The proposed HMM training procedures are able to identify over 90% of channel opportunities with PU load ranging from 20% to 80% of the channel capacity. Also, the collision rates, that is, when both PU and SU would be transmitting concurrently on the channel, was less than 10% for PU load in 30-90% of the channel capacity. Furthermore, the proposed HMM training procedures reduced the collision rate by 45.1% and improved the number of seized opportunities by 4.9%.","PeriodicalId":263773,"journal":{"name":"2021 Ninth International Symposium on Computing and Networking (CANDAR)","volume":"416 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120972077","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}

{"title":"Message from the CANDAR 2021 Organizers","authors":"","doi":"10.1109/candar53791.2021.00005","DOIUrl":"https://doi.org/10.1109/candar53791.2021.00005","url":null,"abstract":"","PeriodicalId":263773,"journal":{"name":"2021 Ninth International Symposium on Computing and Networking (CANDAR)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130429184","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}