2020 IEEE Third International Conference on Artificial Intelligence and Knowledge Engineering (AIKE)最新文献

{"title":"Trust Model to Minimize the Influence of Malicious Attacks in Sharding Based Blockchain Networks","authors":"M. Halgamuge, Samurdika C. Hettikankanamge, Azeem Mohammad","doi":"10.1109/AIKE48582.2020.00032","DOIUrl":"https://doi.org/10.1109/AIKE48582.2020.00032","url":null,"abstract":"A sharding mechanism could potentially be the solution to enhance the scalability of blockchain networks and makes the distributed ledger technology more feasible. Despite the scalability improvement, it increases the influence of malicious attacks on blockchain networks. We develop a comprehensive trust model by enhancing the trust score of nodes to minimize the adversary influences of malicious attacks in sharding based blockchain networks. Firstly, a penalty factor is incorporated into this trust model to decrease the probability of malicious nodes becoming leaders in the shards. Then, we examine the leader selection probability for varying penalty factors. We also observe the influence of the global reputation on the trust score for a varying number of nodes. Secondly, we increase the trustworthiness of nodes by including penalty factors and reputation scores to nodes that could then identify the malicious influence. The fair node distribution among shards is achieved by distributing the nodes with the same aggregated trustworthiness scores. Finally, we develop a probability distribution model to identify the probabilities of clustering corrupted nodes into single shards and the existence of such corrupted shards in the entire network. Uncorrupted or honest shard probability is shown to be higher in the RapidChain than the Elastico and OmniLedger sharding protocols. This could be as a result of the shard resiliency of the RapidChain (n/2) protocol being more significant than that of the Elastico (n/3) and in OmniLedger (n/3) protocols. Low message complexity of single intra-shard consensus of the RapidChain protocol $mathcal{O}(n)$ may contribute to perform security algorithms more efficiently than that of the Elastico $mathcal{O}({n^2})$ and OmniLedger $mathcal{O}(n)$ sharding protocols. The probabilities of clustering corrupted nodes into single shards can be estimated, and the existence of such corrupted shards in entire networks can be identified using the proposed model.","PeriodicalId":370671,"journal":{"name":"2020 IEEE Third International Conference on Artificial Intelligence and Knowledge Engineering (AIKE)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133282066","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":"Artificial Intelligence Design on Embedded Board with Edge Computing for Vehicle Applications","authors":"Ching-Lung Su, W. Lai, Yu-Kai Zhang, Ting-Jia Guo, Yi-Jiun Hung, Hui-Chiao Chen","doi":"10.1109/AIKE48582.2020.00026","DOIUrl":"https://doi.org/10.1109/AIKE48582.2020.00026","url":null,"abstract":"This article proposes advanced driver assistance system (ADAS) from neural network by YOLO v3-tiny on vehicle platform of NXP S32V234 with edge computing to detect pedestrians and knights. The implemented embedded board has limitation to perform a lot of convolution. As proposed design need to reduce the amount of operation, the considered problem of reduced precision at the same time. The proposed architecture uses method of Squeeze Net and quantization to reduce the amount of operation about 46% and the precision has only slightly reduced. The proposed methods of image to column (Im2col) and memory efficient convolution (MEC) rearranges continuous matrix space to access. The proposed hardware of APEX uses to accelerate operations can reduce execution time and increase detection speed by ten multiples compared with YOLO v3-tiny architecture.","PeriodicalId":370671,"journal":{"name":"2020 IEEE Third International Conference on Artificial Intelligence and Knowledge Engineering (AIKE)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114374108","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":"A Defense Method against Poisoning Attacks on IoT Machine Learning Using Poisonous Data","authors":"Tomoki Chiba, Y. Sei, Yasuyuki Tahara, Akihiko Ohsuga","doi":"10.1109/AIKE48582.2020.00022","DOIUrl":"https://doi.org/10.1109/AIKE48582.2020.00022","url":null,"abstract":"Machine learning is a technology with the potential to enrich our lives in many ways. It is expected to be used in various situations. However, the value of attacks on machine learning models is also increasing. Therefore, it is considered to be dangerous to use machine learning without proper planning. Poisoning attacks are one of the attacks that can be launched against machine learning models. Poisoning attacks reduce the accuracy of machine learning models by mixing training data with data created with malicious intent to attack the models. Depending on the scenario, the damage caused by poisoning attacks may lead to large-scale accidents. In this study, we propose a method to protect machine learning models from poisoning attacks. In this paper, we assume an environment in which data obtained from multiple sources is used as training data for machine learning models and present a method suitable for defending against poisoning attacks in such an environment. The proposed method computes the influence of the data obtained from each source on the accuracy of the machine learning model to understand how good each source is. The impact of replacing the data from each source with poisonous data is also calculated. Based on the results of these calculations, the proposed method determines the data removal rate for each data source, which represents the confidence level for determining the degree of harmfulness of the data. The proposed method prevents poisonous data from being mixed with the normal data by removing it according to the removal rate. To evaluate the performance of the proposed method, we compared existing methods with the proposed method based on the accuracy of the model after applying the proposed defensive measure. In this experiment, under the condition that the training data contains 17% of poisonous data, the accuracy of the defended model of the proposed method is 89%, which is higher than 83% obtained using the existing method. This shows that the proposed method improved the performance of the model against poisoning attacks.","PeriodicalId":370671,"journal":{"name":"2020 IEEE Third International Conference on Artificial Intelligence and Knowledge Engineering (AIKE)","volume":"32 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130440063","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":"Evaluation of Classification algorithms for Distributed Denial of Service Attack Detection","authors":"Maulik Gohil, Sathish A. P. Kumar","doi":"10.1109/AIKE48582.2020.00028","DOIUrl":"https://doi.org/10.1109/AIKE48582.2020.00028","url":null,"abstract":"Distributed Denial of Service (DDoS) attacks aims exhausting the target network with malicious traffic, which is a threat to the availability of the service. Many detection systems, specifically Intrusion Detection System (IDS) have been proposed throughout the last two decades as the Internet evolved, although users and organizations find it continuously challenging and defeated while dealing with DDoS. Though, IDS is the first point of defense for protecting critical networks against ever evolving issues of intrusive activities, however it should be up to date all the time to detect any anomalous behavior so that integrity, confidentiality and availability of the service can be preserved. But, the accuracy of new detection methods, techniques, algorithms heavily rely on the existence of well-designed datasets for training purposes and evaluation by creating the classifier model. In this work, experimentation has been carried out using major supervised classification algorithms to classify the DDoS attack accurately from the legitimate flows. Among all the classifier, tree-based classifiers and distance-based classifiers performed the best.","PeriodicalId":370671,"journal":{"name":"2020 IEEE Third International Conference on Artificial Intelligence and Knowledge Engineering (AIKE)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116112120","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":"Explainable and Adaptable Augmentation in Knowledge Attention Network for Multi-Agent Deep Reinforcement Learning Systems","authors":"Joshua Ho, Chien-Min Wang","doi":"10.1109/AIKE48582.2020.00031","DOIUrl":"https://doi.org/10.1109/AIKE48582.2020.00031","url":null,"abstract":"The scale of modem Artificial Intelligence systems has been growing and entering more research territories by incorporating Deep Learning (DL) and Deep Reinforcement Learning (DRL) methods. More specifically, multi-agent DRL methods have been widely applied to address the problems of high-dimensional computation, which interpret the conditions that real-world systems mainly encounter and the issues that require resolving. However, the current approaches of DL and DRL are often challenged for their untransparent and time-consuming modeling processes in their attempt to achieve a practical and applicable inference based on human-level perspective and acceptance. This paper presents an explainable and adaptable augmented knowledge attention network for multi-agent DRL systems, which uses game theory simulation to tackle the problem of non-stationarity at the beginning, while improving the learning exploration built upon the strategic ontology to achieve the learning convergence more efficiently for autonomous agents. We anticipate that our approach will facilitate future research studies and potential research inspections of emerging multi-agent DRL systems for increasingly complex and autonomous environments.","PeriodicalId":370671,"journal":{"name":"2020 IEEE Third International Conference on Artificial Intelligence and Knowledge Engineering (AIKE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130779318","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":"Method for Low-Cost Environment Partitioning Modeling in Dynamic Update","authors":"Takuto Yamauchi, K. Tei, S. Honiden","doi":"10.1109/AIKE48582.2020.00036","DOIUrl":"https://doi.org/10.1109/AIKE48582.2020.00036","url":null,"abstract":"There are systems in the field of event-driven control that require continuous operation. Continuous operation is achieved by switching from normal control to control capable of coping with faults when a fault in the system is detected. In the design phase, the developer needs to create an update controller capable of coping with all possible faults by modeling safe update procedures for any number of possible malfunction patterns. This naturally places a heavy burden on the developer. In this paper, we propose a design method that reduces the design cost of the update environment, which accounts for most of the design burden of an update controller. When designing a new update environment by reusing one that has already been designed, only the design related to the state preservation during update needs to be changed. However, the conventional design method utilizes not only the state preservation relationship but also mixes in two other concerns. Therefore, our proposed method separates the preservation relations of this state from the mixed concerns. We examined the reduction effect of our method in a reuse situation with multiple failure patterns in two systems that require continuous operation and found that the maximum design cost reduction effect was 90% or more.","PeriodicalId":370671,"journal":{"name":"2020 IEEE Third International Conference on Artificial Intelligence and Knowledge Engineering (AIKE)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131402612","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":"Privacy Preserving Chatbot Conversations","authors":"Debmalya Biswas","doi":"10.1109/AIKE48582.2020.00035","DOIUrl":"https://doi.org/10.1109/AIKE48582.2020.00035","url":null,"abstract":"With chatbots gaining traction and their adoption growing in different verticals, e.g. Health, Banking, Dating; and users sharing more and more private information with chatbots - studies have started to highlight the privacy risks of chatbots. In this paper, we propose two privacypreserving approaches for chatbot conversations. The first approach applies ‘entity’ based privacy filtering and transformation, and can be applied directly on the app (client) side. It however requires knowledge of the chatbot design to be enabled. We present a second scheme based on Searchable Encryption that is able to preserve user chat privacy, without requiring any knowledge of the chatbot design. Finally, we present some experimental results based on a real-life employee Help Desk chatbot that validates both the need and feasibility of the proposed approaches.","PeriodicalId":370671,"journal":{"name":"2020 IEEE Third International Conference on Artificial Intelligence and Knowledge Engineering (AIKE)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124548532","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":"Knowledge Graph Visualization: Challenges, Framework, and Implementation","authors":"Rungsiman Nararatwong, N. Kertkeidkachorn, R. Ichise","doi":"10.1109/AIKE48582.2020.00034","DOIUrl":"https://doi.org/10.1109/AIKE48582.2020.00034","url":null,"abstract":"A knowledge graph (KG) is a rich resource representing real-world facts. Visualizing a knowledge graph helps humans gain a deep understanding of the facts, leading to new insights and concepts. However, the massive and complex nature of knowledge graphs has brought many longstanding challenges, especially to attract non-expert users. This paper discusses these challenges; we turned them into a generic knowledge-graph visualization framework, namely KGViz, consisting of four dimensions: modularity, intuitive user interface, performance, and access control. Our implementation of KGViz is a high-capacity, extendable, and scalable KG visualizer, which we designed to promotes community contributions.","PeriodicalId":370671,"journal":{"name":"2020 IEEE Third International Conference on Artificial Intelligence and Knowledge Engineering (AIKE)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115538233","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":"Computational Semantics: How to solve the suspense of supersense","authors":"Aishwarya Asesh","doi":"10.1109/AIKE48582.2020.00024","DOIUrl":"https://doi.org/10.1109/AIKE48582.2020.00024","url":null,"abstract":"Understanding human language is a difficult task, with varied fields of study which aim at explaining and researching the human language principles. Linguistics, Psychology and Computer Science all use domain specific tools to describe and model language. Natural Language Processing is the field which aims at using computational mechanisms to process naturally occurring human language. Modeling syntax gives language structure. Using general sense classes, or \"supersenses\" one can potentially enrich texts with semantic information. Given a sentence with syntactic information, and a closed set of semantic supersenses, can a supersense tagged sentence be derived? Furthermore, can one demarcate boundaries for multiword expressions? The aim of this research study is to create a multiword expression boundary and supersense labelled sentence by training with Word, part-of-speech (POS), multiword expression (MWE) and supersense tagged training data. The semantically tagged sentences can be used for many tasks such as question answering systems, information retrieval, discourse and sentiment analysis.","PeriodicalId":370671,"journal":{"name":"2020 IEEE Third International Conference on Artificial Intelligence and Knowledge Engineering (AIKE)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121018286","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":"Proposed Techniques to Design Speed Efficient Data Warehouse Architecture for Fastening Knowledge Discovery Process","authors":"Abhishek Gupta, Arun Sahayadhas, V. Gupta","doi":"10.1109/AIKE48582.2020.00039","DOIUrl":"https://doi.org/10.1109/AIKE48582.2020.00039","url":null,"abstract":"Decision-making is the key factor of any organization which decides organization’s sustainability in competitive market and its continuous growth and helps in knowledge discovery process. These decisions are taken based on analysis of historical and current data, which are managed by data warehouses (DWH). Based on the datasets provided by these DWH, crystal and ad-hoc reports are generated by BI tools. So, Speed of data warehouse architectures plays a prominent role for deriving decisions at right time. In this paper we have proposed techniques to make data warehouse architecture speed efficient. For speed optimization we have not only worked on data warehouse architecture but also, we have worked on various operations performed by data warehouse, which further boost the overall data warehouse architecture speed.","PeriodicalId":370671,"journal":{"name":"2020 IEEE Third International Conference on Artificial Intelligence and Knowledge Engineering (AIKE)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124108546","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}