Pub Date : 2022-09-05DOI: 10.1109/idsta55301.2022.9923038
{"title":"IDSTA 2022 Cover Page","authors":"","doi":"10.1109/idsta55301.2022.9923038","DOIUrl":"https://doi.org/10.1109/idsta55301.2022.9923038","url":null,"abstract":"","PeriodicalId":268343,"journal":{"name":"2022 International Conference on Intelligent Data Science Technologies and Applications (IDSTA)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128465852","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 : 2022-09-05DOI: 10.1109/IDSTA55301.2022.9923042
Ahmad Al-Omari, A. Allhusen, A. Wahbeh, M. Al-Ramahi, I. Alsmadi
The value and size of information exchanged through dark-web pages are remarkable. Recently Many researches showed values and interests in using machine-learning methods to extract security-related useful knowledge from those dark-web pages. In this scope, our goals in this research focus on evaluating best prediction models while analyzing traffic level data coming from the dark web. Results and analysis showed that feature selection played an important role when trying to identify the best models. Sometimes the right combination of features would increase the model’s accuracy. For some feature set and classifier combinations, the Src Port and Dst Port both proved to be important features. When available, they were always selected over most other features. When absent, it resulted in many other features being selected to compensate for the information they provided. The Protocol feature was never selected as a feature, regardless of whether Src Port and Dst Port were available.
{"title":"Dark Web Analytics: A Comparative Study of Feature Selection and Prediction Algorithms","authors":"Ahmad Al-Omari, A. Allhusen, A. Wahbeh, M. Al-Ramahi, I. Alsmadi","doi":"10.1109/IDSTA55301.2022.9923042","DOIUrl":"https://doi.org/10.1109/IDSTA55301.2022.9923042","url":null,"abstract":"The value and size of information exchanged through dark-web pages are remarkable. Recently Many researches showed values and interests in using machine-learning methods to extract security-related useful knowledge from those dark-web pages. In this scope, our goals in this research focus on evaluating best prediction models while analyzing traffic level data coming from the dark web. Results and analysis showed that feature selection played an important role when trying to identify the best models. Sometimes the right combination of features would increase the model’s accuracy. For some feature set and classifier combinations, the Src Port and Dst Port both proved to be important features. When available, they were always selected over most other features. When absent, it resulted in many other features being selected to compensate for the information they provided. The Protocol feature was never selected as a feature, regardless of whether Src Port and Dst Port were available.","PeriodicalId":268343,"journal":{"name":"2022 International Conference on Intelligent Data Science Technologies and Applications (IDSTA)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132792667","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 : 2022-09-05DOI: 10.1109/IDSTA55301.2022.9923044
N. Menon, Shantanu Saboo, Tanmay Ambadkar, Umesh Uppili
Accurately forecasting energy consumption for buildings has become increasingly important over the years owing to the increasing prices of energy. A good forecast gives an understanding of how much the expected load (demand) of the building would be in the coming days and months. This could be used in further planning of energy usage within the building. This also becomes important due to the dynamic nature of energy rates. With an accurate forecast, one could also aim for spot trading by which the energy is bought and sold at different rates in a daily fashion. We target short-term and medium-term demand forecasting for buildings. Data Sampling is an integral part of training time-series models. The temporal horizon along with the patterns captured contribute to the model learning and thus its forecasts. When the data is aplenty with more than one value per day, the traditional sliding window method is unable to forecast for short-term forecasts without the actual truth values because of its continuous nature. The forecasts deviate very quickly and become unusable. In this paper, we present a novel data sampling technique called Discrete Sequencing. This samples data sequences in a lagged fashion which looks at a much larger temporal horizon with a smaller sequence size. We demonstrate the efficacy of our sampling technique by testing the forecasts on three different neural network architectures.
{"title":"Discrete Sequencing for Demand Forecasting: A novel data sampling technique for time series forecasting","authors":"N. Menon, Shantanu Saboo, Tanmay Ambadkar, Umesh Uppili","doi":"10.1109/IDSTA55301.2022.9923044","DOIUrl":"https://doi.org/10.1109/IDSTA55301.2022.9923044","url":null,"abstract":"Accurately forecasting energy consumption for buildings has become increasingly important over the years owing to the increasing prices of energy. A good forecast gives an understanding of how much the expected load (demand) of the building would be in the coming days and months. This could be used in further planning of energy usage within the building. This also becomes important due to the dynamic nature of energy rates. With an accurate forecast, one could also aim for spot trading by which the energy is bought and sold at different rates in a daily fashion. We target short-term and medium-term demand forecasting for buildings. Data Sampling is an integral part of training time-series models. The temporal horizon along with the patterns captured contribute to the model learning and thus its forecasts. When the data is aplenty with more than one value per day, the traditional sliding window method is unable to forecast for short-term forecasts without the actual truth values because of its continuous nature. The forecasts deviate very quickly and become unusable. In this paper, we present a novel data sampling technique called Discrete Sequencing. This samples data sequences in a lagged fashion which looks at a much larger temporal horizon with a smaller sequence size. We demonstrate the efficacy of our sampling technique by testing the forecasts on three different neural network architectures.","PeriodicalId":268343,"journal":{"name":"2022 International Conference on Intelligent Data Science Technologies and Applications (IDSTA)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132088242","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 : 2022-09-05DOI: 10.1109/IDSTA55301.2022.9923056
Neha Mishra, H. Levkowitz
Blockchain is a fundamental technology that can decentralize how we organize, share, and preserve data and information. This paper evaluates and improves the performance of our Personal Data Vault (our ongoing framework) by focusing on Hyperledger Fabric (HLF) version 2.x (v2.x), one of the most popular open source and highly scalable permissioned blockchains, particularly taking advantage of their new chaincode lifecycle. We conducted several experiments using the Hyperledger Caliper Benchmark version 0.4.2 (v0.4.2), a performance measuring tool. First, we observed changes in performance by varying network parameters (e.g., block size, endorsement policy (EP), number of clients). Then, for further evaluation, we selected sets of network parameters that showed the best performance for a given number of clients. A first selected set of network parameters showed significant improvements in throughput and average latency compared to the parameters that were not selected. And, a second selected set of network parameters out-performed the first in almost every way. These improvements were obtained by using a faster smart contracts lifecycle.
{"title":"Performance Evaluation of Permissioned-based Personal Data Vault Implemented Using Hyperledger Fabric v2.x","authors":"Neha Mishra, H. Levkowitz","doi":"10.1109/IDSTA55301.2022.9923056","DOIUrl":"https://doi.org/10.1109/IDSTA55301.2022.9923056","url":null,"abstract":"Blockchain is a fundamental technology that can decentralize how we organize, share, and preserve data and information. This paper evaluates and improves the performance of our Personal Data Vault (our ongoing framework) by focusing on Hyperledger Fabric (HLF) version 2.x (v2.x), one of the most popular open source and highly scalable permissioned blockchains, particularly taking advantage of their new chaincode lifecycle. We conducted several experiments using the Hyperledger Caliper Benchmark version 0.4.2 (v0.4.2), a performance measuring tool. First, we observed changes in performance by varying network parameters (e.g., block size, endorsement policy (EP), number of clients). Then, for further evaluation, we selected sets of network parameters that showed the best performance for a given number of clients. A first selected set of network parameters showed significant improvements in throughput and average latency compared to the parameters that were not selected. And, a second selected set of network parameters out-performed the first in almost every way. These improvements were obtained by using a faster smart contracts lifecycle.","PeriodicalId":268343,"journal":{"name":"2022 International Conference on Intelligent Data Science Technologies and Applications (IDSTA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129001034","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 : 2022-09-05DOI: 10.1109/IDSTA55301.2022.9923130
Mohammed Ali Kunda, I. Alsmadi
Web application security testing is vital for preventing any security flaws in the design of web applications. A major challenge in web security testing is the continuous change and evolution of web design tools and modules. As such, most open source tools may not be up to date with catching up with recent technologies. In this paper, we reported our effort and experience testing our recently developed website (https://mysmartsa.com/). We utilized and reported vulnerabilities from several open-source security testing tools. We also reported efforts to debug and fix those security issues throughout the development process.
{"title":"Practical web security testing: Evolution of web application modules and open source testing tools","authors":"Mohammed Ali Kunda, I. Alsmadi","doi":"10.1109/IDSTA55301.2022.9923130","DOIUrl":"https://doi.org/10.1109/IDSTA55301.2022.9923130","url":null,"abstract":"Web application security testing is vital for preventing any security flaws in the design of web applications. A major challenge in web security testing is the continuous change and evolution of web design tools and modules. As such, most open source tools may not be up to date with catching up with recent technologies. In this paper, we reported our effort and experience testing our recently developed website (https://mysmartsa.com/). We utilized and reported vulnerabilities from several open-source security testing tools. We also reported efforts to debug and fix those security issues throughout the development process.","PeriodicalId":268343,"journal":{"name":"2022 International Conference on Intelligent Data Science Technologies and Applications (IDSTA)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114219067","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 : 2022-09-05DOI: 10.1109/IDSTA55301.2022.9923049
Ahmed Aleroud, Nour Alhussien, C. Albert
Ongoing research indicates the types of issues that need to be considered by a social cybersecurity researcher or practitioner. This study investigates the existing research on social cyber security on Arabic social media. It suggests the need to consider socio-political issues when presenting computational social media studies. We investigate the scope of social cyberattacks in Arabic. We show the need for new open-source intelligence (OSINT) framework to identify disinformation, bots, trolls, cyborgs, and memes. Recent studies have found that such attacks are spreading in 25 different languages including Arabic; some of these have caused injury and even death. We provide a comprehensive requirement analysis for developing open-source intelligence systems to detect social cyberattacks in Arabic. We show that while there are many OSINT Systems (OSINTs) to mitigate such attacks in English, systems needed to mitigate such attacks in other languages such as Arabic are still limited.
{"title":"From Theory to Practice: Towards an OSINT Framework to Mitigate Arabic Social Cyber Attacks","authors":"Ahmed Aleroud, Nour Alhussien, C. Albert","doi":"10.1109/IDSTA55301.2022.9923049","DOIUrl":"https://doi.org/10.1109/IDSTA55301.2022.9923049","url":null,"abstract":"Ongoing research indicates the types of issues that need to be considered by a social cybersecurity researcher or practitioner. This study investigates the existing research on social cyber security on Arabic social media. It suggests the need to consider socio-political issues when presenting computational social media studies. We investigate the scope of social cyberattacks in Arabic. We show the need for new open-source intelligence (OSINT) framework to identify disinformation, bots, trolls, cyborgs, and memes. Recent studies have found that such attacks are spreading in 25 different languages including Arabic; some of these have caused injury and even death. We provide a comprehensive requirement analysis for developing open-source intelligence systems to detect social cyberattacks in Arabic. We show that while there are many OSINT Systems (OSINTs) to mitigate such attacks in English, systems needed to mitigate such attacks in other languages such as Arabic are still limited.","PeriodicalId":268343,"journal":{"name":"2022 International Conference on Intelligent Data Science Technologies and Applications (IDSTA)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124921027","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 : 2022-09-05DOI: 10.1109/idsta55301.2022.9923046
{"title":"Organization Committee","authors":"","doi":"10.1109/idsta55301.2022.9923046","DOIUrl":"https://doi.org/10.1109/idsta55301.2022.9923046","url":null,"abstract":"","PeriodicalId":268343,"journal":{"name":"2022 International Conference on Intelligent Data Science Technologies and Applications (IDSTA)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124300524","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 : 2022-09-05DOI: 10.1109/IDSTA55301.2022.9923172
Siyamdumisa Maphisa, Duncan Coulter
Biometrics technologies have gained increasing attention across different sectors in the past decade. Face recognition has proven to be one of these successful biometric technologies. For example, law enforcement uses face recognition for faster investigations, banks for identity confirmation, and different organisations for access control. However, face recognition has shortcomings regardless of its high successes, just like any biometrics technology. Face recognition technology is still susceptible to face spoofing attacks despite great efforts made by different researchers to combat such attacks. The study proposes an anti-spoofing model based on deep learning methods. Three different pipelines are implemented based on convolutional neural network (CNN) architecture. A hyper tuned baseline CNN, a convolutional neural network based on AlexNet architecture, and a neural network based on VGG16 architecture. The study benchmarked pipelines using the available face anti-spoofing detection datasets - the NUAA and CelebA datasets. The study measures these performance metrics for all the pipelines: accuracy, precision, recall, F1 score, AUC, and Roc curve. All three pipelines provided good results when tested against the selected datasets.
{"title":"Face Anti-spoofing based on Convolutional Neural Networks","authors":"Siyamdumisa Maphisa, Duncan Coulter","doi":"10.1109/IDSTA55301.2022.9923172","DOIUrl":"https://doi.org/10.1109/IDSTA55301.2022.9923172","url":null,"abstract":"Biometrics technologies have gained increasing attention across different sectors in the past decade. Face recognition has proven to be one of these successful biometric technologies. For example, law enforcement uses face recognition for faster investigations, banks for identity confirmation, and different organisations for access control. However, face recognition has shortcomings regardless of its high successes, just like any biometrics technology. Face recognition technology is still susceptible to face spoofing attacks despite great efforts made by different researchers to combat such attacks. The study proposes an anti-spoofing model based on deep learning methods. Three different pipelines are implemented based on convolutional neural network (CNN) architecture. A hyper tuned baseline CNN, a convolutional neural network based on AlexNet architecture, and a neural network based on VGG16 architecture. The study benchmarked pipelines using the available face anti-spoofing detection datasets - the NUAA and CelebA datasets. The study measures these performance metrics for all the pipelines: accuracy, precision, recall, F1 score, AUC, and Roc curve. All three pipelines provided good results when tested against the selected datasets.","PeriodicalId":268343,"journal":{"name":"2022 International Conference on Intelligent Data Science Technologies and Applications (IDSTA)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132848459","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 : 2022-09-05DOI: 10.1109/IDSTA55301.2022.9923033
A. Shroyer, D. M. Swany
A key challenge of applying machine learning techniques to binary data is the lack of a large corpus of labeled training data. One solution to the lack of real-world data is to create synthetic data from real data through augmentation. In this paper, we demonstrate data augmentation techniques suitable for source code and compiled binary data. By augmenting existing data with semantically-similar sources, training set size is increased, and machine learning models better generalize to unseen data.
{"title":"Data Augmentation for Code Analysis","authors":"A. Shroyer, D. M. Swany","doi":"10.1109/IDSTA55301.2022.9923033","DOIUrl":"https://doi.org/10.1109/IDSTA55301.2022.9923033","url":null,"abstract":"A key challenge of applying machine learning techniques to binary data is the lack of a large corpus of labeled training data. One solution to the lack of real-world data is to create synthetic data from real data through augmentation. In this paper, we demonstrate data augmentation techniques suitable for source code and compiled binary data. By augmenting existing data with semantically-similar sources, training set size is increased, and machine learning models better generalize to unseen data.","PeriodicalId":268343,"journal":{"name":"2022 International Conference on Intelligent Data Science Technologies and Applications (IDSTA)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124040416","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 : 2022-09-05DOI: 10.1109/IDSTA55301.2022.9923040
John Olamofe, Xishuang Dong, Lijun Qian, Eric Shields
Object detection in overhead imagery is of great importance in computer vision. xView is one of the largest publicly available datasets of overhead imagery. Because limited amount of data/images is available for training, the performance of a typical object detection model is expected to be poor without enough training data. In this paper, data augmentation methods by changing/perturbing some of the properties of the images such as changing the color channel of the object, adding salt noise to the object, and enhancing contrast are applied to the xView dataset. Performance evaluation of object detection using YOLOv3 model and augmented data has been carried out. The results demonstrate that the effectiveness of the data augmentation methods depends on both the specific method and the object classes.
{"title":"Performance Evaluation of Data Augmentation for Object Detection in XView Dataset","authors":"John Olamofe, Xishuang Dong, Lijun Qian, Eric Shields","doi":"10.1109/IDSTA55301.2022.9923040","DOIUrl":"https://doi.org/10.1109/IDSTA55301.2022.9923040","url":null,"abstract":"Object detection in overhead imagery is of great importance in computer vision. xView is one of the largest publicly available datasets of overhead imagery. Because limited amount of data/images is available for training, the performance of a typical object detection model is expected to be poor without enough training data. In this paper, data augmentation methods by changing/perturbing some of the properties of the images such as changing the color channel of the object, adding salt noise to the object, and enhancing contrast are applied to the xView dataset. Performance evaluation of object detection using YOLOv3 model and augmented data has been carried out. The results demonstrate that the effectiveness of the data augmentation methods depends on both the specific method and the object classes.","PeriodicalId":268343,"journal":{"name":"2022 International Conference on Intelligent Data Science Technologies and Applications (IDSTA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130887727","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：