Pub Date : 2020-02-01DOI: 10.23919/ICACT48636.2020.9061401
Da-Yu Kao, Yun-Ya Chen, Fuching Tsai
With the rapid development of information technology, cybercrimes are getting increasingly rampant. The popularity of various toolkits facilitates the cyber-attackers to intrude on online systems and access the vast streams of sensitive data. Prevention is better than cure. Penetration testing (PT) not only defends the illegal attacks but also identify potential vulnerabilities. It is capable of distinguishing network traffic on the massive amount of collected data from the following three phases: data reduction, data analysis, and data classification. This paper analyzes the PT network traffic and observes their tool marks.
{"title":"Hacking Tool Identification in Penetration Testing","authors":"Da-Yu Kao, Yun-Ya Chen, Fuching Tsai","doi":"10.23919/ICACT48636.2020.9061401","DOIUrl":"https://doi.org/10.23919/ICACT48636.2020.9061401","url":null,"abstract":"With the rapid development of information technology, cybercrimes are getting increasingly rampant. The popularity of various toolkits facilitates the cyber-attackers to intrude on online systems and access the vast streams of sensitive data. Prevention is better than cure. Penetration testing (PT) not only defends the illegal attacks but also identify potential vulnerabilities. It is capable of distinguishing network traffic on the massive amount of collected data from the following three phases: data reduction, data analysis, and data classification. This paper analyzes the PT network traffic and observes their tool marks.","PeriodicalId":296763,"journal":{"name":"2020 22nd International Conference on Advanced Communication Technology (ICACT)","volume":"415 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122858649","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}
Pub Date : 2020-02-01DOI: 10.23919/ICACT48636.2020.9061565
Zhongtao Chen, De Meng, Yufan Zhang, Tinglin Xin, Ding Xiao
Electricity theft causes significant harm to social and economic development. In the past few years, it has attracted much attention that electricity theft detection based on electricity consumption data can help to solve this problem. A major challenge is that there are no explicit features in electricity consumption records. However, the existing machine learning-based detection methods mainly suffer from the following two disadvantages. (1) Handcrafted features and shallow-architecture classifiers have poor detection accuracy. (2) Most methods consider electricity consumption as static and cannot capture both the internal time-series natures and external influence factors well. To overcome the above shortcomings, we propose a novel method called Electricity Theft Detection using Deep Bidirectional Recurrent Neural Network (ETD-DBRNN), which can capture the internal characteristics and the external correlation by learning the electricity consumption records and influence factors representation. Experiments on real-world datasets validate the effectiveness of our method.
{"title":"Electricity Theft Detection Using Deep Bidirectional Recurrent Neural Network","authors":"Zhongtao Chen, De Meng, Yufan Zhang, Tinglin Xin, Ding Xiao","doi":"10.23919/ICACT48636.2020.9061565","DOIUrl":"https://doi.org/10.23919/ICACT48636.2020.9061565","url":null,"abstract":"Electricity theft causes significant harm to social and economic development. In the past few years, it has attracted much attention that electricity theft detection based on electricity consumption data can help to solve this problem. A major challenge is that there are no explicit features in electricity consumption records. However, the existing machine learning-based detection methods mainly suffer from the following two disadvantages. (1) Handcrafted features and shallow-architecture classifiers have poor detection accuracy. (2) Most methods consider electricity consumption as static and cannot capture both the internal time-series natures and external influence factors well. To overcome the above shortcomings, we propose a novel method called Electricity Theft Detection using Deep Bidirectional Recurrent Neural Network (ETD-DBRNN), which can capture the internal characteristics and the external correlation by learning the electricity consumption records and influence factors representation. Experiments on real-world datasets validate the effectiveness of our method.","PeriodicalId":296763,"journal":{"name":"2020 22nd International Conference on Advanced Communication Technology (ICACT)","volume":"148 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123448627","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}
Pub Date : 2020-02-01DOI: 10.23919/ICACT48636.2020.9061515
Khasanboy Kodirov, Khusanboy Kodirov, Young Sil Lee
One of the most important things that humans need in their life is communication. Communication helps to spread knowledge, information and different forms of relationships between people. Unfortunately, millions of people around the world are unable to enjoy this blessing. With this in mind, the number of communication devices, applications, systems, strategies and tools that replace or support natural speech is increasing rapidly. This paper describes an AAC software we developed that helps both disabled children and adults to communicate easily with other people especially in office work, school or social gatherings. To use this software, users should input a sentence and it will converted to audio speech using built-in voices for male or female. In addition to that, it can convert voice that received by microphone into text and display it on the screen for deaf people to read.
{"title":"Implementation of web application based on Augmentative and Alternative Communication (AAC) method for People with Hearing and Speech Impairment","authors":"Khasanboy Kodirov, Khusanboy Kodirov, Young Sil Lee","doi":"10.23919/ICACT48636.2020.9061515","DOIUrl":"https://doi.org/10.23919/ICACT48636.2020.9061515","url":null,"abstract":"One of the most important things that humans need in their life is communication. Communication helps to spread knowledge, information and different forms of relationships between people. Unfortunately, millions of people around the world are unable to enjoy this blessing. With this in mind, the number of communication devices, applications, systems, strategies and tools that replace or support natural speech is increasing rapidly. This paper describes an AAC software we developed that helps both disabled children and adults to communicate easily with other people especially in office work, school or social gatherings. To use this software, users should input a sentence and it will converted to audio speech using built-in voices for male or female. In addition to that, it can convert voice that received by microphone into text and display it on the screen for deaf people to read.","PeriodicalId":296763,"journal":{"name":"2020 22nd International Conference on Advanced Communication Technology (ICACT)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123553265","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 advent of the Internet of Things and digital marketing has changed the way businesses operate and their interactions with consumers. The digital economy has percolated a wide range of industries and smartphones have ingrained into the consumer's lifestyle. The demand for customized services and goods has increased. However, this leaves the consumers' privacy at stake. Current researches have been conducted on IoT and its security threats, its utility in specific retail space for customer marketing. This kind of research has been limited to certain industries and marketing paradigms. A need to summarize IoT and the marketing potential it offers and the social impact this has on consumer behavior is a research gap we aim to address. The current paper's primary purpose is to reflect upon the concept of marketing 4.0 and the fact that the ever-increasing number of IoT devices are connected and transmitting enormous personal data regularly, to determine a person's personality traits and influence their decisions. Further IoT related ethical marketing strategies are outlined.
{"title":"IoT and Modern Marketing: Its Social Implications","authors":"Anooksha Yogesh Rathod, Shubham Pandya, Nishant Doshi","doi":"10.23919/ICACT48636.2020.9061210","DOIUrl":"https://doi.org/10.23919/ICACT48636.2020.9061210","url":null,"abstract":"The advent of the Internet of Things and digital marketing has changed the way businesses operate and their interactions with consumers. The digital economy has percolated a wide range of industries and smartphones have ingrained into the consumer's lifestyle. The demand for customized services and goods has increased. However, this leaves the consumers' privacy at stake. Current researches have been conducted on IoT and its security threats, its utility in specific retail space for customer marketing. This kind of research has been limited to certain industries and marketing paradigms. A need to summarize IoT and the marketing potential it offers and the social impact this has on consumer behavior is a research gap we aim to address. The current paper's primary purpose is to reflect upon the concept of marketing 4.0 and the fact that the ever-increasing number of IoT devices are connected and transmitting enormous personal data regularly, to determine a person's personality traits and influence their decisions. Further IoT related ethical marketing strategies are outlined.","PeriodicalId":296763,"journal":{"name":"2020 22nd International Conference on Advanced Communication Technology (ICACT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128524020","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}
Pub Date : 2020-02-01DOI: 10.23919/ICACT48636.2020.9061430
Nakhoon Choi, Heeyoul Kim
Recently, with the increase of smart factories, smart cities, and the 4th industrial revolution, internal user authentication is emerging as an important issue. The existing user authentication and Access Control architecture can use the centralized system to forge access history by the service manager, which can cause problems such as evasion of responsibility and internal corruption. In addition, the user must independently manage the ID or physical authentication medium for authentication of each service, it is difficult to manage the subscribed services. This paper proposes a Hybrid blockchain-based integrated ID model to solve the above problems. The user creates authentication information based on the electronic signature of the Ethereum Account, a public blockchain, and provides authentication to a service provider composed of a Hyperledger Fabric, a private blockchain. The service provider ensures the integrity of the information by recording the Access History and authentication information in the Internal-Ledger. Through the proposed architecture, we can integrate the physical pass or application for user authentication and authorization into one Unification ID. Service providers can prevent non-Repudiation of responsibility by recording their authority and access history in ledger.
{"title":"Hybrid Blockchain-based Unification ID in Smart Environment","authors":"Nakhoon Choi, Heeyoul Kim","doi":"10.23919/ICACT48636.2020.9061430","DOIUrl":"https://doi.org/10.23919/ICACT48636.2020.9061430","url":null,"abstract":"Recently, with the increase of smart factories, smart cities, and the 4th industrial revolution, internal user authentication is emerging as an important issue. The existing user authentication and Access Control architecture can use the centralized system to forge access history by the service manager, which can cause problems such as evasion of responsibility and internal corruption. In addition, the user must independently manage the ID or physical authentication medium for authentication of each service, it is difficult to manage the subscribed services. This paper proposes a Hybrid blockchain-based integrated ID model to solve the above problems. The user creates authentication information based on the electronic signature of the Ethereum Account, a public blockchain, and provides authentication to a service provider composed of a Hyperledger Fabric, a private blockchain. The service provider ensures the integrity of the information by recording the Access History and authentication information in the Internal-Ledger. Through the proposed architecture, we can integrate the physical pass or application for user authentication and authorization into one Unification ID. Service providers can prevent non-Repudiation of responsibility by recording their authority and access history in ledger.","PeriodicalId":296763,"journal":{"name":"2020 22nd International Conference on Advanced Communication Technology (ICACT)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127303882","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}
Pub Date : 2020-02-01DOI: 10.23919/ICACT48636.2020.9061408
Anh H. Dang, W. Kameyama
In this paper, we aim to produce the state-of-the-art semantic segmentation for street fashion photos with three contributions. Firstly, we propose a high-performance semantic segmentation network that follows the encoder-decoder structure. Secondly, we propose a guided training process using multiple auxiliary losses. And thirdly, the 2D max-pooling-based scaling operation to produce segmentation feature maps for the aforementioned guided training process. We also propose mIoU+ metric taking noise into account for better evaluation. Evaluations with the ModaNet data set show that the proposed network achieves high benchmark results with less computational cost compared to ever-proposed methods.
{"title":"Robust Semantic Segmentation for Street Fashion Photos","authors":"Anh H. Dang, W. Kameyama","doi":"10.23919/ICACT48636.2020.9061408","DOIUrl":"https://doi.org/10.23919/ICACT48636.2020.9061408","url":null,"abstract":"In this paper, we aim to produce the state-of-the-art semantic segmentation for street fashion photos with three contributions. Firstly, we propose a high-performance semantic segmentation network that follows the encoder-decoder structure. Secondly, we propose a guided training process using multiple auxiliary losses. And thirdly, the 2D max-pooling-based scaling operation to produce segmentation feature maps for the aforementioned guided training process. We also propose mIoU+ metric taking noise into account for better evaluation. Evaluations with the ModaNet data set show that the proposed network achieves high benchmark results with less computational cost compared to ever-proposed methods.","PeriodicalId":296763,"journal":{"name":"2020 22nd International Conference on Advanced Communication Technology (ICACT)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116829594","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}
Pub Date : 2020-02-01DOI: 10.23919/ICACT48636.2020.9061558
Dongseop Lee, Hyunjin Kim, Jaecheol Ryou
Recently, deep learning technology has been applied to various fields with high performance and various services. Image recognition is also used in various fields with high performance by incorporating deep learning technology. However, deep learning technology is vulnerable to evasion attacks that cause the model to be misclassified by modulating the original image. In this paper, we generate an adversarial example using the forward-backward-splitting iterative procedure. Then perform an evasion attack on the show and tell model.
{"title":"Evasion Attack in Show and Tell Model","authors":"Dongseop Lee, Hyunjin Kim, Jaecheol Ryou","doi":"10.23919/ICACT48636.2020.9061558","DOIUrl":"https://doi.org/10.23919/ICACT48636.2020.9061558","url":null,"abstract":"Recently, deep learning technology has been applied to various fields with high performance and various services. Image recognition is also used in various fields with high performance by incorporating deep learning technology. However, deep learning technology is vulnerable to evasion attacks that cause the model to be misclassified by modulating the original image. In this paper, we generate an adversarial example using the forward-backward-splitting iterative procedure. Then perform an evasion attack on the show and tell model.","PeriodicalId":296763,"journal":{"name":"2020 22nd International Conference on Advanced Communication Technology (ICACT)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114926707","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}
Pub Date : 2020-02-01DOI: 10.23919/ICACT48636.2020.9061281
Minjae Byun, Yongjun Lee, Jin-Young Choi
Model checking is a method of verifying whether a target system satisfies a specific property using mathematical and logical proofs. Model checking tools to verify design (1) require a formal description of the design and (2) there can be discrepancies between the model and actual implementation. To solve these problems, various tools such as CBMC and BLAST that can directly input C codes have been proposed. However, in terms of security, it is difficult to figure out which software weaknesses these tools can verify. In this paper, we matched the properties that CBMC can verify with corresponding CWEs, considering interdependencies of CWEs. We also conducted an experiment using Juliet Test Suite to check CBMC can actually verify the codes including these CWEs.
模型检验是一种利用数学和逻辑证明验证目标系统是否满足特定属性的方法。验证设计的模型检查工具(1)需要对设计进行正式描述，(2)模型和实际实现之间可能存在差异。为了解决这些问题，人们提出了各种可以直接输入C代码的工具，如CBMC、BLAST等。然而，就安全性而言，很难确定这些工具可以验证哪些软件弱点。在本文中，我们将CBMC可以验证的属性与相应的CWEs进行匹配，考虑到CWEs之间的相互依赖性。我们还使用Juliet Test Suite进行了一个实验，以检查CBMC是否可以实际验证包含这些CWEs的代码。
{"title":"Analysis of software weakness detection of CBMC based on CWE","authors":"Minjae Byun, Yongjun Lee, Jin-Young Choi","doi":"10.23919/ICACT48636.2020.9061281","DOIUrl":"https://doi.org/10.23919/ICACT48636.2020.9061281","url":null,"abstract":"Model checking is a method of verifying whether a target system satisfies a specific property using mathematical and logical proofs. Model checking tools to verify design (1) require a formal description of the design and (2) there can be discrepancies between the model and actual implementation. To solve these problems, various tools such as CBMC and BLAST that can directly input C codes have been proposed. However, in terms of security, it is difficult to figure out which software weaknesses these tools can verify. In this paper, we matched the properties that CBMC can verify with corresponding CWEs, considering interdependencies of CWEs. We also conducted an experiment using Juliet Test Suite to check CBMC can actually verify the codes including these CWEs.","PeriodicalId":296763,"journal":{"name":"2020 22nd International Conference on Advanced Communication Technology (ICACT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131099893","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}
Pub Date : 2020-02-01DOI: 10.23919/ICACT48636.2020.9061405
Da-Yu Kao, Fang-Yu Lu, Fuching Tsai
Law enforcement agencies (LEAs) face a challenging problem to detect the tool marks of Skype traffic. Analyzing digital packets is an essential job in digital forensics. This study collects these packets, traces their routings, analyzes the relevant information, and explores the tool mark identification of Skype packets. It uses experimental data on a personal computer, investigates the characteristics of Skype traffic, and provides a tool mark analysis of network traffic. The study can assist the investigator in identifying the suspect using a Skype communication application to commit the crime.
{"title":"Tool Mark Identification of Skype Traffic","authors":"Da-Yu Kao, Fang-Yu Lu, Fuching Tsai","doi":"10.23919/ICACT48636.2020.9061405","DOIUrl":"https://doi.org/10.23919/ICACT48636.2020.9061405","url":null,"abstract":"Law enforcement agencies (LEAs) face a challenging problem to detect the tool marks of Skype traffic. Analyzing digital packets is an essential job in digital forensics. This study collects these packets, traces their routings, analyzes the relevant information, and explores the tool mark identification of Skype packets. It uses experimental data on a personal computer, investigates the characteristics of Skype traffic, and provides a tool mark analysis of network traffic. The study can assist the investigator in identifying the suspect using a Skype communication application to commit the crime.","PeriodicalId":296763,"journal":{"name":"2020 22nd International Conference on Advanced Communication Technology (ICACT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130614053","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}
Pub Date : 2020-02-01DOI: 10.23919/ICACT48636.2020.9061388
M. Rana, A. Abdelhadi
Development of an electricity market model is very important step of forecasting power of generators and client demand. This paper proposes a day-ahead state-space power system model which is obtained by a set of partial differential equations. After simplifications, the 4th order user-friendly state-space power system model is obtained where the measurements are obtained by a set of sensors. Secondly, we proposed an H-infinity based power system states forecasting algorithm where process and measurement noise covariances are not need to know. In each iteration, the residual error between true and forecasted states are minimised lead to an accurate forecasted system states. Numerical simulation illustrates that the proposed scheme can able to forecast the system states within 1–12 seconds.
{"title":"Day-Ahead Electricity Market State-Space Model and Its Power Production, Demand and Price Forecasting Algorithm Using H-infinity Filter","authors":"M. Rana, A. Abdelhadi","doi":"10.23919/ICACT48636.2020.9061388","DOIUrl":"https://doi.org/10.23919/ICACT48636.2020.9061388","url":null,"abstract":"Development of an electricity market model is very important step of forecasting power of generators and client demand. This paper proposes a day-ahead state-space power system model which is obtained by a set of partial differential equations. After simplifications, the 4th order user-friendly state-space power system model is obtained where the measurements are obtained by a set of sensors. Secondly, we proposed an H-infinity based power system states forecasting algorithm where process and measurement noise covariances are not need to know. In each iteration, the residual error between true and forecasted states are minimised lead to an accurate forecasted system states. Numerical simulation illustrates that the proposed scheme can able to forecast the system states within 1–12 seconds.","PeriodicalId":296763,"journal":{"name":"2020 22nd International Conference on Advanced Communication Technology (ICACT)","volume":"138 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129123660","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：