R. Hassanpour, Erdogan Dogdu, R. Choupani, Onur Goker, Nazli Nazli
Phishing e-mails are considered as spam e-mails, which aim to collect sensitive personal information about the users via network. Since the main purpose of this behavior is mostly to harm users financially, it is vital to detect these phishing or spam e-mails immediately to prevent unauthorized access to users' vital information. To detect phishing e-mails, using a quicker and robust classification method is important. Considering the billions of e-mails on the Internet, this classification process is supposed to be done in a limited time to analyze the results. In this work, we present some of the early results on the classification of spam email using deep learning and machine methods. We utilize word2vec to represent emails instead of using the popular keyword or other rule-based methods. Vector representations are then fed into a neural network to create a learning model. We have tested our method on an open dataset and found over 96% accuracy levels with the deep learning classification methods in comparison to the standard machine learning algorithms.
{"title":"Phishing e-mail detection by using deep learning algorithms","authors":"R. Hassanpour, Erdogan Dogdu, R. Choupani, Onur Goker, Nazli Nazli","doi":"10.1145/3190645.3190719","DOIUrl":"https://doi.org/10.1145/3190645.3190719","url":null,"abstract":"Phishing e-mails are considered as spam e-mails, which aim to collect sensitive personal information about the users via network. Since the main purpose of this behavior is mostly to harm users financially, it is vital to detect these phishing or spam e-mails immediately to prevent unauthorized access to users' vital information. To detect phishing e-mails, using a quicker and robust classification method is important. Considering the billions of e-mails on the Internet, this classification process is supposed to be done in a limited time to analyze the results. In this work, we present some of the early results on the classification of spam email using deep learning and machine methods. We utilize word2vec to represent emails instead of using the popular keyword or other rule-based methods. Vector representations are then fed into a neural network to create a learning model. We have tested our method on an open dataset and found over 96% accuracy levels with the deep learning classification methods in comparison to the standard machine learning algorithms.","PeriodicalId":403177,"journal":{"name":"Proceedings of the ACMSE 2018 Conference","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123029013","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}
S. North, Adnan Rashied, J. Walters, A. Alissa, Josh Cooper, E. Rawls, Cheyenne Sancho, Utku Victor Sahin, K. Randell, Heather Rego
The main objective of this study is to find efficient methods to utilize brain-computer interfaces (BCIs) in conjunction with aerial drones. The study investigates how effective the EPOC+ is by challenging users of diverse genders and ages to complete tasks using mental commands and facial expressions to control a Parrot AR-Drone 2.0. After a calibration phase, the designed experiments were conducted using randomly selected participants (n=20). Preliminary analysis of the collected data indicated that there was no significant difference between the rating of difficulty before and after, between the mental and facial commands. Furthermore, this study showed that from group of participants more individuals had greater difficulty controlling the mental and facial commands than they originally expected.
{"title":"Performance analysis of brain-computer interfaces in aerial drone","authors":"S. North, Adnan Rashied, J. Walters, A. Alissa, Josh Cooper, E. Rawls, Cheyenne Sancho, Utku Victor Sahin, K. Randell, Heather Rego","doi":"10.1145/3190645.3190683","DOIUrl":"https://doi.org/10.1145/3190645.3190683","url":null,"abstract":"The main objective of this study is to find efficient methods to utilize brain-computer interfaces (BCIs) in conjunction with aerial drones. The study investigates how effective the EPOC+ is by challenging users of diverse genders and ages to complete tasks using mental commands and facial expressions to control a Parrot AR-Drone 2.0. After a calibration phase, the designed experiments were conducted using randomly selected participants (n=20). Preliminary analysis of the collected data indicated that there was no significant difference between the rating of difficulty before and after, between the mental and facial commands. Furthermore, this study showed that from group of participants more individuals had greater difficulty controlling the mental and facial commands than they originally expected.","PeriodicalId":403177,"journal":{"name":"Proceedings of the ACMSE 2018 Conference","volume":"195 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116531606","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}
Malware, short for Malicious Software, is growing continuously in numbers and sophistication as our digital world continuous to grow. It is a very serious problem and many efforts are devoted to malware detection in today's cybersecurity world. Many machine learning algorithms are used for the automatic detection of malware in recent years. Most recently, deep learning is being used with better performance. Deep learning models are shown to work much better in the analysis of long sequences of system calls. In this paper a shallow deep learning-based feature extraction method (word2vec) is used for representing any given malware based on its opcodes. Gradient Boosting algorithm is used for the classification task. Then, k-fold cross-validation is used to validate the model performance without sacrificing a validation split. Evaluation results show up to 96% accuracy with limited sample data.
{"title":"Malware classification using deep learning methods","authors":"B. Cakir, Erdogan Dogdu","doi":"10.1145/3190645.3190692","DOIUrl":"https://doi.org/10.1145/3190645.3190692","url":null,"abstract":"Malware, short for Malicious Software, is growing continuously in numbers and sophistication as our digital world continuous to grow. It is a very serious problem and many efforts are devoted to malware detection in today's cybersecurity world. Many machine learning algorithms are used for the automatic detection of malware in recent years. Most recently, deep learning is being used with better performance. Deep learning models are shown to work much better in the analysis of long sequences of system calls. In this paper a shallow deep learning-based feature extraction method (word2vec) is used for representing any given malware based on its opcodes. Gradient Boosting algorithm is used for the classification task. Then, k-fold cross-validation is used to validate the model performance without sacrificing a validation split. Evaluation results show up to 96% accuracy with limited sample data.","PeriodicalId":403177,"journal":{"name":"Proceedings of the ACMSE 2018 Conference","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123992009","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}
Fractal Image Compression is rarely used in high-quality image compression situation because of its long encoding time and inefficiency of encoding book structure. This paper introduces a novel searchless fractal encoding algorithm based on full quadtree range block partition that can efficiently encode 2x2 range blocks or even individual pixels. This approach addresses both problems and thus can be used to perform high-quality image compression. Experimental results show that the algorithm is capable of providing superior performance in achieving better compression ratio and reconstructed image quality compared to traditional search-based and searchless fractal methods in both low and high compression rates. Another advantage of the algorithm is its fast encoding speed since no search process is needed in this approach. The encoding time of this algorithm is only a fraction of traditional fractal algorithms.
{"title":"A full quadtree searchless IFS fractal image encoding algorithm applicable in both high and low compression rates","authors":"Kairai Chen, Xianwei Wu","doi":"10.1145/3190645.3190669","DOIUrl":"https://doi.org/10.1145/3190645.3190669","url":null,"abstract":"Fractal Image Compression is rarely used in high-quality image compression situation because of its long encoding time and inefficiency of encoding book structure. This paper introduces a novel searchless fractal encoding algorithm based on full quadtree range block partition that can efficiently encode 2x2 range blocks or even individual pixels. This approach addresses both problems and thus can be used to perform high-quality image compression. Experimental results show that the algorithm is capable of providing superior performance in achieving better compression ratio and reconstructed image quality compared to traditional search-based and searchless fractal methods in both low and high compression rates. Another advantage of the algorithm is its fast encoding speed since no search process is needed in this approach. The encoding time of this algorithm is only a fraction of traditional fractal algorithms.","PeriodicalId":403177,"journal":{"name":"Proceedings of the ACMSE 2018 Conference","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122900242","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}
Modern cryptography builds upon many of the concepts introduced in classical cryptography. This study contributes to research in these fields through a cryptanalysis of a polyalphabetic substitution cipher known as Autokey using Friedman's index of coincidence measure of text character frequency paired with modern computer programming and data collection techniques. Results indicate that under certain constraints on the encrypting key, the index of coincidence can be applied to text decrypted using a small sample of random keys of various lengths to accurately predict the length of the encryption key.
{"title":"A cryptanalysis of the autokey cipher using the index of coincidence","authors":"Derek C. Brown","doi":"10.1145/3190645.3190679","DOIUrl":"https://doi.org/10.1145/3190645.3190679","url":null,"abstract":"Modern cryptography builds upon many of the concepts introduced in classical cryptography. This study contributes to research in these fields through a cryptanalysis of a polyalphabetic substitution cipher known as Autokey using Friedman's index of coincidence measure of text character frequency paired with modern computer programming and data collection techniques. Results indicate that under certain constraints on the encrypting key, the index of coincidence can be applied to text decrypted using a small sample of random keys of various lengths to accurately predict the length of the encryption key.","PeriodicalId":403177,"journal":{"name":"Proceedings of the ACMSE 2018 Conference","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124157178","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}
Thomas Willingham, Cody Henderson, Blair Kiel, Md Shariful Haque, T. Atkison
Bluetooth Low Energy (BTLE) is pervasive in technology throughout all areas of our lives. In this research effort, experiments are performed to discover vulnerabilities in the Bluetooth protocol and given the right technology determine exploitation. Using a Bluetooth keyboard, practical examples of the Bluetooth Low Energy protocol were able to be provided. Because of the results garnered, it is recommended that Bluetooth Low Energy not be used for any connections that may transmit sensitive data, or with devices that may have access to sensitive networks.
{"title":"Testing vulnerabilities in bluetooth low energy","authors":"Thomas Willingham, Cody Henderson, Blair Kiel, Md Shariful Haque, T. Atkison","doi":"10.1145/3190645.3190693","DOIUrl":"https://doi.org/10.1145/3190645.3190693","url":null,"abstract":"Bluetooth Low Energy (BTLE) is pervasive in technology throughout all areas of our lives. In this research effort, experiments are performed to discover vulnerabilities in the Bluetooth protocol and given the right technology determine exploitation. Using a Bluetooth keyboard, practical examples of the Bluetooth Low Energy protocol were able to be provided. Because of the results garnered, it is recommended that Bluetooth Low Energy not be used for any connections that may transmit sensitive data, or with devices that may have access to sensitive networks.","PeriodicalId":403177,"journal":{"name":"Proceedings of the ACMSE 2018 Conference","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122928779","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}
With the increasing popularity of microblogging and social media platforms like Twitter, researchers are trying to make use of the massive amount of user-created data to explore new applications/tools. Success of research in data science is highly dependent on the amount and type of data collected. For this effort, a thesaurus-based query expansion technique from information retrieval will be used to extract additional Twitter data. Though there has been research in this general area, our effort concentrates on applying a thesaurus-based query expansion for Twitter retrieval. Experiments are performed to collect Twitter data using the proposed approach for query terms related to disaster situations like hurricanes and shootings. We observed an increase of 32% in tweets received for the Hurricane Harvey event, and a 131% increase in the volume of tweets for a query related to the Vegas shooting incidence using the thesaurus-based query expansion approach.
{"title":"Preliminary research on thesaurus-based query expansion for Twitter data extraction","authors":"Vidya Nakade, A. Musaev, T. Atkison","doi":"10.1145/3190645.3190694","DOIUrl":"https://doi.org/10.1145/3190645.3190694","url":null,"abstract":"With the increasing popularity of microblogging and social media platforms like Twitter, researchers are trying to make use of the massive amount of user-created data to explore new applications/tools. Success of research in data science is highly dependent on the amount and type of data collected. For this effort, a thesaurus-based query expansion technique from information retrieval will be used to extract additional Twitter data. Though there has been research in this general area, our effort concentrates on applying a thesaurus-based query expansion for Twitter retrieval. Experiments are performed to collect Twitter data using the proposed approach for query terms related to disaster situations like hurricanes and shootings. We observed an increase of 32% in tweets received for the Hurricane Harvey event, and a 131% increase in the volume of tweets for a query related to the Vegas shooting incidence using the thesaurus-based query expansion approach.","PeriodicalId":403177,"journal":{"name":"Proceedings of the ACMSE 2018 Conference","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130408099","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}
Useful programs often fall into obsolescence when they are not updated with the advancing hardware and software. This presentation describes an exercise on deploying a legacy software for a latent variable analysis. Although the need to use this software arose in the context of a multidisciplinary project, including bioinformatics, the goal of this exercise is to provide a better understanding of the challenges in preserving programs developed on hardware that may no longer exist or used out-of-date or earlier versions of operations systems and compilers. Such programs may be required to maintain reproducibility of previously published experiments and used to further contribute to research.
{"title":"An exercise in repeating experimental analysis using a program developed on a no longer available computing system","authors":"L. D. Castro, J. Jaromczyk","doi":"10.1145/3190645.3190720","DOIUrl":"https://doi.org/10.1145/3190645.3190720","url":null,"abstract":"Useful programs often fall into obsolescence when they are not updated with the advancing hardware and software. This presentation describes an exercise on deploying a legacy software for a latent variable analysis. Although the need to use this software arose in the context of a multidisciplinary project, including bioinformatics, the goal of this exercise is to provide a better understanding of the challenges in preserving programs developed on hardware that may no longer exist or used out-of-date or earlier versions of operations systems and compilers. Such programs may be required to maintain reproducibility of previously published experiments and used to further contribute to research.","PeriodicalId":403177,"journal":{"name":"Proceedings of the ACMSE 2018 Conference","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126378412","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}
In this paper, we introduce a model for donation verification. A randomized algorithm is developed to check if the money claimed being received by the collector is (1 - ϵ)-approximation to the total amount money contributed by the donors. We also derive some negative results that show it is impossible to verify the donations under some circumstances.
{"title":"A model for donation verification","authors":"Bin Fu, F. Zhu, J. Abraham","doi":"10.1145/3190645.3190698","DOIUrl":"https://doi.org/10.1145/3190645.3190698","url":null,"abstract":"In this paper, we introduce a model for donation verification. A randomized algorithm is developed to check if the money claimed being received by the collector is (1 - ϵ)-approximation to the total amount money contributed by the donors. We also derive some negative results that show it is impossible to verify the donations under some circumstances.","PeriodicalId":403177,"journal":{"name":"Proceedings of the ACMSE 2018 Conference","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126673029","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":"Proceedings of the ACMSE 2018 Conference","authors":"","doi":"10.1145/3190645","DOIUrl":"https://doi.org/10.1145/3190645","url":null,"abstract":"","PeriodicalId":403177,"journal":{"name":"Proceedings of the ACMSE 2018 Conference","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121900032","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：