Proceedings of the 16th ACM International Conference on Computing Frontiers最新文献

Using community detection for spatial networks: POSTER 利用社区检测空间网络:POSTER

Proceedings of the 16th ACM International Conference on Computing Frontiers Pub Date : 2019-04-30 DOI: 10.1145/3310273.3323429

Krista Rizman Žalik, B. Žalik

引用次数: 0

Optimization and deployment of CNNs at the edge: the ALOHA experience cnn在边缘的优化和部署:ALOHA体验

Proceedings of the 16th ACM International Conference on Computing Frontiers Pub Date : 2019-04-30 DOI: 10.1145/3310273.3323435

P. Meloni, Daniela Loi, Paola Busia, Gianfranco Deriu, A. Pimentel, Dolly Sapra, T. Stefanov, S. Minakova, Francesco Conti, L. Benini, Maura Pintor, B. Biggio, Bernhard Moser, Natalia Shepeleva, N. Fragoulis, Ilias Theodorakopoulos, M. Masin, F. Palumbo

{"title":"Optimization and deployment of CNNs at the edge: the ALOHA experience","authors":"P. Meloni, Daniela Loi, Paola Busia, Gianfranco Deriu, A. Pimentel, Dolly Sapra, T. Stefanov, S. Minakova, Francesco Conti, L. Benini, Maura Pintor, B. Biggio, Bernhard Moser, Natalia Shepeleva, N. Fragoulis, Ilias Theodorakopoulos, M. Masin, F. Palumbo","doi":"10.1145/3310273.3323435","DOIUrl":"https://doi.org/10.1145/3310273.3323435","url":null,"abstract":"Deep learning (DL) algorithms have already proved their effectiveness on a wide variety of application domains, including speech recognition, natural language processing, and image classification. To foster their pervasive adoption in applications where low latency, privacy issues and data bandwidth are paramount, the current trend is to perform inference tasks at the edge. This requires deployment of DL algorithms on low-energy and resource-constrained computing nodes, often heterogenous and parallel, that are usually more complex to program and to manage without adequate support and experience. In this paper, we present ALOHA, an integrated tool flow that tries to facilitate the design of DL applications and their porting on embedded heterogenous architectures. The proposed tool flow aims at automating different design steps and reducing development costs. ALOHA considers hardware-related variables and security, power efficiency, and adaptivity aspects during the whole development process, from pre-training hyperparameter optimization and algorithm configuration to deployment.","PeriodicalId":431860,"journal":{"name":"Proceedings of the 16th ACM International Conference on Computing Frontiers","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125692236","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: 11

On the maximum function in stochastic computing 论随机计算中的极大函数

Proceedings of the 16th ACM International Conference on Computing Frontiers Pub Date : 2019-04-30 DOI: 10.1145/3310273.3323050

Florian Neugebauer, I. Polian, J. Hayes

引用次数: 7

Anytime instructions for programmable accuracy floating-point arithmetic 随时指令可编程精度浮点运算

Proceedings of the 16th ACM International Conference on Computing Frontiers Pub Date : 2019-04-30 DOI: 10.1145/3310273.3322833

Marcel Brand, Michael Witterauf, Frank Hannig, Jürgen Teich

引用次数: 4

Parallel algorithms through approximation: graphs, data privacy and machine learning 通过近似的并行算法:图，数据隐私和机器学习

Proceedings of the 16th ACM International Conference on Computing Frontiers Pub Date : 2019-04-30 DOI: 10.1145/3310273.3323431

A. Pothen

引用次数: 0

A new memory reliability technique for multiple bit upsets mitigation 一种新的存储可靠性多比特干扰缓解技术

Proceedings of the 16th ACM International Conference on Computing Frontiers Pub Date : 2019-04-30 DOI: 10.1145/3310273.3321564

Alexandre Chabot, Ihsen Alouani, S. Niar, R. Nouacer

引用次数: 1

A privacy-preserving protocol for indoor wi-fi localization 用于室内wi-fi定位的隐私保护协议

Proceedings of the 16th ACM International Conference on Computing Frontiers Pub Date : 2019-04-30 DOI: 10.1145/3310273.3323400

S. N. Eshun, P. Palmieri

{"title":"A privacy-preserving protocol for indoor wi-fi localization","authors":"S. N. Eshun, P. Palmieri","doi":"10.1145/3310273.3323400","DOIUrl":"https://doi.org/10.1145/3310273.3323400","url":null,"abstract":"Location-aware applications have witnessed massive worldwide growth in recent years due to the introduction and advancement of smartphones. Most of these applications rely on the Global Positioning System (GPS) which is not available in indoor environments. As a result, Wi-Fi fingerprinting is becoming increasingly popular as an alternative as it allows localizing users in indoor environments, has lower power consumption, and is also more economical as it does not require a dedicated sensor other than a Wi-Fi card. The technique allows a service provider (SP) to construct a Wi-Fi database (called radio map) that can be used as a reference point to localize a user. However, this process does not preserve the user privacy, as the location can only be computed interactively with the SP. The service provider may also reveal sensitive information on the indoor space (e.g. the building map) to the user. Thus, we need an indoor localization protocol that addresses the privacy of both parties. In this paper, we present a privacy-preserving cryptographic protocol for indoor Wi-Fi localization, that prevents the SP from learning the exact location of the user outside of certain pre-defined sensitive areas, while keeping the SP's database secure. Thus, both parties cannot learn anything about each other's input beyond the implicit output revealed.","PeriodicalId":431860,"journal":{"name":"Proceedings of the 16th ACM International Conference on Computing Frontiers","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134126751","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

Will sentiment of forex news effect forecast of the RMB exchange rate?: POSTER 外汇消息的情绪会影响人民币汇率的预测吗?:海报

Proceedings of the 16th ACM International Conference on Computing Frontiers Pub Date : 2019-04-30 DOI: 10.1145/3310273.3323422

Zhou Cheng, Jixiang Wang, T. Qi, Junfeng Zhao, Zhihong Wang, Yi Guo, Yu Zhou

引用次数: 0

The parameter optimization based on LVPSO algorithm for detecting multi-step attacks 基于LVPSO算法的参数优化检测多步攻击

Proceedings of the 16th ACM International Conference on Computing Frontiers Pub Date : 2019-04-30 DOI: 10.1145/3310273.3323048

Jianguo Jiang, Qiwen Wang, Zhixin Shi, Bin Lv, W. Fan, Xiao Peng

{"title":"The parameter optimization based on LVPSO algorithm for detecting multi-step attacks","authors":"Jianguo Jiang, Qiwen Wang, Zhixin Shi, Bin Lv, W. Fan, Xiao Peng","doi":"10.1145/3310273.3323048","DOIUrl":"https://doi.org/10.1145/3310273.3323048","url":null,"abstract":"How to detect intrusion attacks is a big challenge for network administrators since the attacks involve multi-step nowadays. The hidden markov model (HMM) is widely used in the field of multi-step attacks detection. However, the existing traditional Baum-Welch algorithm of HMM has two shortcomings: one is the number of attack states need to be determined in advance, the other is the algorithm may make the parameters converge to a local (not overall) optimal solution. In this paper, we propose a novel LVPSO-HMM algorithm based on variable length particle swarm optimization, which solves the shortcomings mentioned above. Concretely, it can optimize the number of attack states when the attacks state is unknown and it can make the model parameters converge to a global optimal solution. Then, we present a multi-step attack detection model architecture whose main idea is, when the number of attack states is unknown in the actual network environment LVPSO-HMM algorithm is used to solve the problem of relying on prior knowledge in current detection. Experiments on the well-known Darpa2000 dataset verify the efficiency of the method.","PeriodicalId":431860,"journal":{"name":"Proceedings of the 16th ACM International Conference on Computing Frontiers","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115853533","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

Examining the practical side channel resilience of ARX-boxes arx -box侧通道弹性的实际检验

Proceedings of the 16th ACM International Conference on Computing Frontiers Pub Date : 2019-04-30 DOI: 10.1145/3310273.3323399

Yan Yan, E. Oswald

引用次数: 6