Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems最新文献_第2页

Malware classification using byte sequence information 恶意软件分类使用字节序列信息

Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems Pub Date : 2018-10-09 DOI: 10.1145/3264746.3264775

Byungho Jung, Taeguen Kim, E. Im

{"title":"Malware classification using byte sequence information","authors":"Byungho Jung, Taeguen Kim, E. Im","doi":"10.1145/3264746.3264775","DOIUrl":"https://doi.org/10.1145/3264746.3264775","url":null,"abstract":"The number of new malware and new malware variants have been increasing continuously. Security experts analyze malware to capture the malicious properties of malware and to generate signatures or detection rules, but the analysis overheads keep increasing with the increasing number of malware. To analyze a large amount of malware, various kinds of automatic analysis methods are in need. Recently, deep learning techniques such as convolutional neural network (CNN) and recurrent neural network (RNN) have been applied for malware classifications. The features used in the previous approches are mostly based on API (Application Programming Interface) information, and the API invocation information can be obtained through dynamic analysis. However, the invocation information may not reflect malicious behaviors of malware because malware developers use various analysis avoidance techniques. Therefore, deep learning-based malware analysis using other features still need to be developed to improve malware analysis performance. In this paper, we propose a malware classification method using the deep learning algorithm based on byte information. Our proposed method uses images generated from malware byte information that can reflect malware behavioral context, and the convolutional neural network-based sentence analysis is used to process the generated images. We performed several experiments to show the effecitveness of our proposed method, and the experimental results show that our method showed higher accuracy than the naive CNN model, and the detection accuracy was about 99%.","PeriodicalId":186790,"journal":{"name":"Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132138664","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}

引用次数: 14

Dynamic tuning of applications using restricted transactional memory 使用受限事务性内存的应用程序的动态调优

Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems Pub Date : 2018-10-09 DOI: 10.1145/3264746.3264789

Shih-Kai Lin, Ding-Yong Hong, Sheng-Yu Fu, Jan-Jan Wu, W. Hsu

{"title":"Dynamic tuning of applications using restricted transactional memory","authors":"Shih-Kai Lin, Ding-Yong Hong, Sheng-Yu Fu, Jan-Jan Wu, W. Hsu","doi":"10.1145/3264746.3264789","DOIUrl":"https://doi.org/10.1145/3264746.3264789","url":null,"abstract":"Transactional Synchronization Extensions (TSX) support for hardware Transactional Memory (TM) on Intel 4th generation Core processors. Two programming interfaces, Hardware Lock Elision (HLE) and Restricted Transactional Memory (RTM), are provided to support software development using TSX. HLE is easy to use and maintains backward compatible with processors without TSX support while RTM is more flexible and scalable. Previous researches have shown that critical sections protected by RTM with a well-designed retry mechanism as its fallback code path can often achieve better performance than HLE. More parallel programs may be programmed in HLE, however, using RTM may obtain greater performance. To embrace both productivity and high performance of parallel program with TSX, we present a framework built on QEMU that can dynamically transform HLE instructions in an application binary to fragments of RTM codes with adaptive tuning on the fly. Compared to HLE execution, our prototype achieves 1.56x speedup with 8 threads on average. Due to the scalability of RTM, the speedup will be more significant as the number of threads increases.","PeriodicalId":186790,"journal":{"name":"Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127949073","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}

引用次数: 0

Aspect oriented context-aware and event-driven data processing for internet of things 面向方面、上下文感知和事件驱动的物联网数据处理

Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems Pub Date : 2018-10-09 DOI: 10.1145/3264746.3264761

Michal Trnka, J. Svacina, T. Cerný, Eunjee Song

引用次数: 0

Acceleration of Monte-Carlo simulation on high performance computing platforms 蒙特卡罗仿真在高性能计算平台上的加速

Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems Pub Date : 2018-10-09 DOI: 10.1145/3264746.3264765

Pei-Jen Wang, C. Liu, Chia-Heng Tu, Chen-Pang Lee, Shih-Hao Hung

引用次数: 1

Energy-balancing unequal concentric chain clustering (MIMO-UCC) protocol for IoT system in 5G environment 5G环境下物联网系统能量平衡不平等同心链聚类(MIMO-UCC)协议

Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems Pub Date : 2018-10-09 DOI: 10.1145/3264746.3264747

Mohammad Baniata, Hyunho Ji, Yongmin Kim, Jeongwoo Choi, Jiman Hong

{"title":"Energy-balancing unequal concentric chain clustering (MIMO-UCC) protocol for IoT system in 5G environment","authors":"Mohammad Baniata, Hyunho Ji, Yongmin Kim, Jeongwoo Choi, Jiman Hong","doi":"10.1145/3264746.3264747","DOIUrl":"https://doi.org/10.1145/3264746.3264747","url":null,"abstract":"To improve people life quality or experience, recently the concept of IoT technology has been introduced with a higher degree of variability in term communication capability and applied applications comparing with WSN. The devices in such kind of technology are implanted with multiple radio access interfaces, usually indicated as Multiple-In and Multiple-Out (MIMO) in 5G networks. With the propagation of MIMO service in IoT machines, clustering technique for IoT systems is required to achieve energy efficiency. In this paper, we propose a novel centralized Energy -Balancing Unequal Concentric Chain Clustering (MIMO-UCC) protocol for the IoT system in the context of the 5G environment. Which has a probability-based suboptimal multi-hop path selection algorithm to reduce the burden on the cluster head and adjusting the cluster-head diameter based on the energy level and the distance to the base station. MIMO-UCC use principal vector projection approach, which considers the location of the base station to build an unequal concentric chain clustering.","PeriodicalId":186790,"journal":{"name":"Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125652541","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}

引用次数: 4

Dynamic bandwidth allocation in SDN based next generation virtual networks: a deterministic network calculus approach 基于SDN的下一代虚拟网络动态带宽分配:一种确定性网络演算方法

Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems Pub Date : 2018-10-09 DOI: 10.1145/3264746.3264754

Ahyoung Lee, Pu Wang, Shih-Chun Lin, I. Akyildiz, Min Luo

{"title":"Dynamic bandwidth allocation in SDN based next generation virtual networks: a deterministic network calculus approach","authors":"Ahyoung Lee, Pu Wang, Shih-Chun Lin, I. Akyildiz, Min Luo","doi":"10.1145/3264746.3264754","DOIUrl":"https://doi.org/10.1145/3264746.3264754","url":null,"abstract":"Software-defined networking (SDN), recognized as next-generation paradigm, decouples the network control plane from the data forwarding plane for a logically centralized controller, allowing rapid networking technology innovations to serve great varieties of users' applications. SDN empowers the evolution of Internet with Open-Flow (OF) and taking advantages of Network Virtualization (NV) to provide efficient service slicing strategies. One of key research issues in both SDN and NV environments is a lack of resource scheduling mechanisms in the physical infrastructure. The resource scheduling mechanisms should be highly capable of ensuring network stability to add further benefits to SDN based next generation virtual networks. We propose a service discipline of dynamic bandwidth scheduling (DBS) within OF switches that dynamically allocates data rates to flows regarding QoS and flow dynamics. Furthermore, we formulate a coherent analysis framework of scheduling disciplines as a mathematical model based on the deterministic network calculus to provide a fast characterization of deterministic service guarantees in SDN. Finally, simulations validate derived theoretical bounds from the analysis framework and confirm that the DBS discipline guarantees QoS of all flows through dynamic bandwidth allocation and ensures an efficient allocation of system bandwidth.","PeriodicalId":186790,"journal":{"name":"Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129920915","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}

引用次数: 5

Data center traffic scheduling with hot-cold link detection capabilities 具有冷热链路检测能力的数据中心流量调度

Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems Pub Date : 2018-10-09 DOI: 10.1145/3264746.3264797

A. Yazidi, Hussein Abdi, Boning Feng

{"title":"Data center traffic scheduling with hot-cold link detection capabilities","authors":"A. Yazidi, Hussein Abdi, Boning Feng","doi":"10.1145/3264746.3264797","DOIUrl":"https://doi.org/10.1145/3264746.3264797","url":null,"abstract":"Software-Defined Networking (SDN) has been one of the most discussed areas in computer networking over the last years. The field has raised an extensive amount of research, and led to a transformation of traditional network architectures. The architecture of SDN enables the separation of the control and data planes and centralizes the network intelligence. Today's data center networks are clusters of thousands of machines. The most used routing protocol in Data centers is Equal-Cost Multi-Path Protocol (ECMP) which relies on a per-flow static hashing that is known to cause bandwidth loss because of long term collisions. In this paper, a traffic engineering approach built on the concept of SDN is presented that aims to enhance the least-loaded link routing mechanism with intelligent monitoring capabilities. In this perspective, we introduce Hot and Cold link detection (HCLD) mechanism. Our HCLD permits to dynamically re-route heavy flows from heavily utilized links (Hot links) while attracting more flows to lowly utilized links (Cold links). Comprehensive experimental results show that the devised flow scheduling solution outperforms the widely used ECMP. Results also demonstrate that dynamic monitoring of traffic statistics could be used to better utilize the total available bandwidth of the network in a reactive manner.","PeriodicalId":186790,"journal":{"name":"Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127127869","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}

引用次数: 2

Travel planning problem considering site selection and itinerary making 考虑选址和行程制定的旅行计划问题

Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems Pub Date : 2018-10-09 DOI: 10.1145/3264746.3264781

Du Jiaoman, Li Lei, Li Xiang

引用次数: 2

Automatic knowledge extraction from OCR documents using hierarchical document analysis 使用分层文档分析从OCR文档中自动提取知识

Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems Pub Date : 2018-10-09 DOI: 10.1145/3264746.3264793

Mohammad Masum, S. Kosaraju, Tanju Bayramoglu, Girish Modgil, Mingon Kang

引用次数: 3

Efficient synthetic light field generation using adaptive multi-level rendering 高效合成光场生成使用自适应多层次渲染

Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems Pub Date : 2018-10-09 DOI: 10.1145/3264746.3264759

Liang-Chi Tseng, W. Hsu

{"title":"Efficient synthetic light field generation using adaptive multi-level rendering","authors":"Liang-Chi Tseng, W. Hsu","doi":"10.1145/3264746.3264759","DOIUrl":"https://doi.org/10.1145/3264746.3264759","url":null,"abstract":"Real-time global illumination rendering is very desirable for emerging applications such as Virtual Reality (VR) and Augmented Reality (AR). However, client devices have difficulties to support photorealistic rendering, such as Ray-Tracing, due to insufficient computing resources. Many modern frameworks adopted Light Field rendering to support device displaying. A Light Field can be pre-computed and store in cloud. During runtime, the display extracts the colors from the Light Field to generate arbitrary real time viewpoints or re-focusing within a predefined area. To efficiently compute the Light Field, We have combined DIBR (Depth-Image-Based-Rendering) and traditional ray-tracing in an adaptive fashion to synthesize images. By measuring the color errors during runtime, we adaptively determine the right balance between DIBR and Ray Tracing. To further optimize the computation efficiency, we also added a multi-level design to exploit the degree of shareable pixels among images to control the computation for error removal. Experiments show that we achieved up to 3.24X speedup in Light Field generation for relative simple scenes like Cornell Box, and about 2X speed up for complex scenes like Conference Room or Sponza.","PeriodicalId":186790,"journal":{"name":"Proceedings of the 2018 Conference on Research in Adaptive and Convergent Systems","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134461315","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}

引用次数: 0