Pub Date : 2020-10-28DOI: 10.1109/UEMCON51285.2020.9298029
Xianghong Lin, Hang Lu, Xiaomei Pi, Xiangwen Wang
In the innovative neural prostheses, the biological cell assemblies of the biological nervous system can be replaced by artificial organs, which makes the idea of dynamically interface biological neurons even more urgent. To mimic and investigate the activity of biological neural networks, many different architectures and technologies in the field of neuromorphic have been developed at present. When structuring simple neuron models, researchers use Field programmable gate arrays (FPGAs) to obtain better accuracy and real-time performance. This paper uses FPGAs to achieve the circuit design of the neuron model, such that based on the biologically plausible the quadratic spiking neuron model, can simulate the neuron spiking behaviors of thalamus neurons and hippocampal CA1 pyramidal neurons. After the FPGA hardware architecture of the neuron model is designed and implemented, this model can better simulate the spiking behaviors observed in biological neurons.
{"title":"An FPGA-based Implementation Method for Quadratic Spiking Neuron Model","authors":"Xianghong Lin, Hang Lu, Xiaomei Pi, Xiangwen Wang","doi":"10.1109/UEMCON51285.2020.9298029","DOIUrl":"https://doi.org/10.1109/UEMCON51285.2020.9298029","url":null,"abstract":"In the innovative neural prostheses, the biological cell assemblies of the biological nervous system can be replaced by artificial organs, which makes the idea of dynamically interface biological neurons even more urgent. To mimic and investigate the activity of biological neural networks, many different architectures and technologies in the field of neuromorphic have been developed at present. When structuring simple neuron models, researchers use Field programmable gate arrays (FPGAs) to obtain better accuracy and real-time performance. This paper uses FPGAs to achieve the circuit design of the neuron model, such that based on the biologically plausible the quadratic spiking neuron model, can simulate the neuron spiking behaviors of thalamus neurons and hippocampal CA1 pyramidal neurons. After the FPGA hardware architecture of the neuron model is designed and implemented, this model can better simulate the spiking behaviors observed in biological neurons.","PeriodicalId":433609,"journal":{"name":"2020 11th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122646649","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 : 2020-10-28DOI: 10.1109/UEMCON51285.2020.9298081
Juliet E. McKenna, Tyler R. Hopkins, Lucas T. Lavallee, D. Dow
Knee injuries are difficult to accurately diagnose. The manual evaluation relies on many subjective factors such as physician experience, swelling, patient guarding, and the severity of the injury. These factors can lead to an inaccurate or incomplete diagnosis, resulting in less than optimal treatment and recovery. Knee injuries are very common among athletes and can occur during the day to day activities, with many resulting in tears to one or more of the four ligaments. For evaluation, a physician manually manipulates the knee with a series of standard tests. Even though these standard manual tests are considered best practice, they are known to lead to some inaccuracies with upwards of 1 in 8 patients being misdiagnosed due to testing deficiencies. Imaging by MRI is used to support the diagnosis if available, though not available to all patients due to cost and time requirements. This purpose of this project was to develop and test a wearable diagnostic system contained within a sleeve over the knee. Incorporated sensors were used to monitor movement and electromyographic activity to determine quantitative measurements toward a diagnosis. The movement and displacement monitoring subsystems were tested on a constructed model of the lower leg and knee. Preliminary results have shown accurate readings with an average percent error of 1% for range of motion testing and 3% (0.1 to 0.2 mm) for laxity testing. This measurement determined by this system could be reported to a physician who could use when making a diagnosis. Improved diagnosis would guide appropriate treatment and contribute to improved recovery.
{"title":"Knee Injury Diagnostic Device","authors":"Juliet E. McKenna, Tyler R. Hopkins, Lucas T. Lavallee, D. Dow","doi":"10.1109/UEMCON51285.2020.9298081","DOIUrl":"https://doi.org/10.1109/UEMCON51285.2020.9298081","url":null,"abstract":"Knee injuries are difficult to accurately diagnose. The manual evaluation relies on many subjective factors such as physician experience, swelling, patient guarding, and the severity of the injury. These factors can lead to an inaccurate or incomplete diagnosis, resulting in less than optimal treatment and recovery. Knee injuries are very common among athletes and can occur during the day to day activities, with many resulting in tears to one or more of the four ligaments. For evaluation, a physician manually manipulates the knee with a series of standard tests. Even though these standard manual tests are considered best practice, they are known to lead to some inaccuracies with upwards of 1 in 8 patients being misdiagnosed due to testing deficiencies. Imaging by MRI is used to support the diagnosis if available, though not available to all patients due to cost and time requirements. This purpose of this project was to develop and test a wearable diagnostic system contained within a sleeve over the knee. Incorporated sensors were used to monitor movement and electromyographic activity to determine quantitative measurements toward a diagnosis. The movement and displacement monitoring subsystems were tested on a constructed model of the lower leg and knee. Preliminary results have shown accurate readings with an average percent error of 1% for range of motion testing and 3% (0.1 to 0.2 mm) for laxity testing. This measurement determined by this system could be reported to a physician who could use when making a diagnosis. Improved diagnosis would guide appropriate treatment and contribute to improved recovery.","PeriodicalId":433609,"journal":{"name":"2020 11th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131120339","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 : 2020-10-28DOI: 10.1109/UEMCON51285.2020.9298128
Ilker Kara, M. Aydos
Currently as the widespread use of virtual monetary units (like Bitcoin, Ethereum, Ripple, Litecoin) has begun, people with bad intentions have been attracted to this area and have produced and marketed ransomware in order to obtain virtual currency easily. This ransomware infiltrates the victim’s system with smartly-designed methods and encrypts the files found in the system. After the encryption process, the attacker leaves a message demanding a ransom in virtual currency to open access to the encrypted files and warns that otherwise the files will not be accessible. This type of ransomware is becoming more popular over time, so currently it is the largest information technology security threat. In the literature, there are many studies about detection and analysis of this cyber-bullying. In this study, we focused on crypto-ransomware and investigated a forensic analysis of a current attack example in detail. In this example, the attack method and behavior of the crypto-ransomware were analyzed and it was identified that information belonging to the attacker was accessible. With this dimension, we think our study will significantly contribute to the struggle against this threat.
{"title":"Cyber Fraud: Detection and Analysis of the Crypto-Ransomware","authors":"Ilker Kara, M. Aydos","doi":"10.1109/UEMCON51285.2020.9298128","DOIUrl":"https://doi.org/10.1109/UEMCON51285.2020.9298128","url":null,"abstract":"Currently as the widespread use of virtual monetary units (like Bitcoin, Ethereum, Ripple, Litecoin) has begun, people with bad intentions have been attracted to this area and have produced and marketed ransomware in order to obtain virtual currency easily. This ransomware infiltrates the victim’s system with smartly-designed methods and encrypts the files found in the system. After the encryption process, the attacker leaves a message demanding a ransom in virtual currency to open access to the encrypted files and warns that otherwise the files will not be accessible. This type of ransomware is becoming more popular over time, so currently it is the largest information technology security threat. In the literature, there are many studies about detection and analysis of this cyber-bullying. In this study, we focused on crypto-ransomware and investigated a forensic analysis of a current attack example in detail. In this example, the attack method and behavior of the crypto-ransomware were analyzed and it was identified that information belonging to the attacker was accessible. With this dimension, we think our study will significantly contribute to the struggle against this threat.","PeriodicalId":433609,"journal":{"name":"2020 11th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128056307","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 : 2020-10-28DOI: 10.1109/UEMCON51285.2020.9298172
P. Gorday, N. Erdöl, H. Zhuang
Incremental learning after deployment is one of several attractive capabilities that motivate the use of neural network demodulators. This paper presents a complex noncoherent neural network suitable for on-off key (OOK) demodulation. When trained in an AWGN channel, the demodulator learns a solution that outperforms the traditional noncoherent matched filter demodulator. The paper also explores incremental learning techniques that enable continued learning in the field. Training in the field with known labels provides maximum adaptability to new conditions, but the availability of known symbols maybe limited. As an alternative, we considered the effectiveness of entropy regularization and pseudo-labels to adapt a lab-trained reference network to new field conditions. Simulation of these techniques in an example multipath channel demonstrates successful unsupervised adaptation with initial symbol error rates up to 20% and successful semi-supervised adaptation with a small fraction of known symbols per packet and initial symbol error rates as high as 40%. In both cases, symbol error rates after adaptation are below 0.3%.
{"title":"A Noncoherent Incremental Learning Demodulator","authors":"P. Gorday, N. Erdöl, H. Zhuang","doi":"10.1109/UEMCON51285.2020.9298172","DOIUrl":"https://doi.org/10.1109/UEMCON51285.2020.9298172","url":null,"abstract":"Incremental learning after deployment is one of several attractive capabilities that motivate the use of neural network demodulators. This paper presents a complex noncoherent neural network suitable for on-off key (OOK) demodulation. When trained in an AWGN channel, the demodulator learns a solution that outperforms the traditional noncoherent matched filter demodulator. The paper also explores incremental learning techniques that enable continued learning in the field. Training in the field with known labels provides maximum adaptability to new conditions, but the availability of known symbols maybe limited. As an alternative, we considered the effectiveness of entropy regularization and pseudo-labels to adapt a lab-trained reference network to new field conditions. Simulation of these techniques in an example multipath channel demonstrates successful unsupervised adaptation with initial symbol error rates up to 20% and successful semi-supervised adaptation with a small fraction of known symbols per packet and initial symbol error rates as high as 40%. In both cases, symbol error rates after adaptation are below 0.3%.","PeriodicalId":433609,"journal":{"name":"2020 11th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","volume":"207 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132576807","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 : 2020-10-28DOI: 10.1109/UEMCON51285.2020.9298085
Aristide T.-J. Akem, Edwin Mugume
With the rapidly increasing demand for cellular network services, operators have responded by deploying more base stations (BSs) which have greatly increased the total energy consumption of cellular network infrastructure. In this paper, machine learning is used to exploit temporal variations in cellular network traffic. Four machine learning algorithms and one conventional time series forecasting method are used for traffic prediction and then compared. Results show that random forest regression performs best with a coefficient of determination of 0.82 on the whole dataset and 0.84 on data of isolated days of the week. Based on the predicted traffic, three sleep mode schemes are applied to a homogeneous network. Simulation results show that the strategic sleep mode scheme performs best with an 87.4% energy saving gain over the conventional scheme and a 32% percent energy saving gain over the random scheme for a given day. In addition, the strategic scheme achieves an hourly average power saving of 3,836 W per kilometer squared, which proves that machine learning traffic prediction-based sleep modes are instrumental in achieving energy-efficient cellular networks.
{"title":"A Machine Learning Approach to Temporal Traffic-Aware Energy-Efficient Cellular Networks","authors":"Aristide T.-J. Akem, Edwin Mugume","doi":"10.1109/UEMCON51285.2020.9298085","DOIUrl":"https://doi.org/10.1109/UEMCON51285.2020.9298085","url":null,"abstract":"With the rapidly increasing demand for cellular network services, operators have responded by deploying more base stations (BSs) which have greatly increased the total energy consumption of cellular network infrastructure. In this paper, machine learning is used to exploit temporal variations in cellular network traffic. Four machine learning algorithms and one conventional time series forecasting method are used for traffic prediction and then compared. Results show that random forest regression performs best with a coefficient of determination of 0.82 on the whole dataset and 0.84 on data of isolated days of the week. Based on the predicted traffic, three sleep mode schemes are applied to a homogeneous network. Simulation results show that the strategic sleep mode scheme performs best with an 87.4% energy saving gain over the conventional scheme and a 32% percent energy saving gain over the random scheme for a given day. In addition, the strategic scheme achieves an hourly average power saving of 3,836 W per kilometer squared, which proves that machine learning traffic prediction-based sleep modes are instrumental in achieving energy-efficient cellular networks.","PeriodicalId":433609,"journal":{"name":"2020 11th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133747337","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 : 2020-10-28DOI: 10.1109/UEMCON51285.2020.9298097
Narayana Darapaneni, D. Nikam, Anagha Lomate, Vaibhav Kherde, Swanand Katdare, A. Paduri, Kameswara Rao, Anima Shukla
The COVID-19 (SARS-CoV-2) pandemic is a major global health threat. According to the World Health Organization (WHO) COVID-19 situation report as on June 13, 2020, a total of 7,553,182 confirmed cases and 423,349 deaths have been reported across the world. Total confirmed cases in India as on 30th March’20 is 1071 of which 942 are active COVID-19 cases. There have been 29 death cases. Methods: We had used the mathematical model which monitors the five compartments namely, Susceptible, Exposed, Infected, Recovered and Deaths, collectively expressed as SEIRD to derive the epidemic curve on India and top two most affected states (Maharashtra and Delhi). We also used ARIMA and Logistic Regression model on India data set and two states to p confirmed cases and calculated R-Squared value. Results: As per the model, the growth rate is 4.25, India is likely to reach a peak by August, showing a gradual decrease by end of October or Mid November. Conclusion: Our SEIRD model was good in foreseeing the number of confirmed cases of COVID-19 for the upcoming days, we additionally reproduced the spread of disease in India for next 100 days by utilizing SEIRD model and anticipating the quantity of affirmed cases for next 14 days through ARIMA and Logistic Regression.
{"title":"Coronavirus Outburst Prediction in India using SEIRD, Logistic Regression and ARIMA Model","authors":"Narayana Darapaneni, D. Nikam, Anagha Lomate, Vaibhav Kherde, Swanand Katdare, A. Paduri, Kameswara Rao, Anima Shukla","doi":"10.1109/UEMCON51285.2020.9298097","DOIUrl":"https://doi.org/10.1109/UEMCON51285.2020.9298097","url":null,"abstract":"The COVID-19 (SARS-CoV-2) pandemic is a major global health threat. According to the World Health Organization (WHO) COVID-19 situation report as on June 13, 2020, a total of 7,553,182 confirmed cases and 423,349 deaths have been reported across the world. Total confirmed cases in India as on 30th March’20 is 1071 of which 942 are active COVID-19 cases. There have been 29 death cases. Methods: We had used the mathematical model which monitors the five compartments namely, Susceptible, Exposed, Infected, Recovered and Deaths, collectively expressed as SEIRD to derive the epidemic curve on India and top two most affected states (Maharashtra and Delhi). We also used ARIMA and Logistic Regression model on India data set and two states to p confirmed cases and calculated R-Squared value. Results: As per the model, the growth rate is 4.25, India is likely to reach a peak by August, showing a gradual decrease by end of October or Mid November. Conclusion: Our SEIRD model was good in foreseeing the number of confirmed cases of COVID-19 for the upcoming days, we additionally reproduced the spread of disease in India for next 100 days by utilizing SEIRD model and anticipating the quantity of affirmed cases for next 14 days through ARIMA and Logistic Regression.","PeriodicalId":433609,"journal":{"name":"2020 11th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125348632","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 : 2020-10-28DOI: 10.1109/UEMCON51285.2020.9298170
Shafinaz Islam, Damian Valles, M. Forstner
Audio signal analysis has become prominent in biological domains toward applications in detecting endangered or threatened species like Houston toad and Crawfish frog. Researchers at Texas State University and Texas A&M University are working on a project to rescue these species and understanding the causes of their decline. Currently the researchers are using an Automated Recording Device (ARD), Toadphone 1, an embedded solution designed for only Houston toad call detection. However, this device's software solution has shown limited success in identifying toad calls consequent of high false-positive rates. This paper experimented with a modified software solution for existing ARD, which is capable of detecting Houston toad and Crawfish frog calls with decreased false-positive rates. Six experiments to detect the calls were designed by using thirty-nine Mel-Frequency Cepstral Coefficients (MFCCs) with delta and delta-delta coefficients and sixteen Spectral Sub-band Centroids (SSCs) as audio features within Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRUs) as the classifiers. Results show that LSTM as the classifier with thirty-nine MFCCs audio features, and a 20% validation split produces the highest accuracy for detecting Houston toad and Crawfish frog calls. This architecture has gained 84.7% training, 82.05% validation accuracy, and 84.2% test accuracy with 91.4% test accuracy on Houston toad call and 77.1% on Crawfish frog call.
{"title":"Performance Analysis and Evaluation of LSTM and GRU Architectures for Houston toad and Crawfish frog Call Detection","authors":"Shafinaz Islam, Damian Valles, M. Forstner","doi":"10.1109/UEMCON51285.2020.9298170","DOIUrl":"https://doi.org/10.1109/UEMCON51285.2020.9298170","url":null,"abstract":"Audio signal analysis has become prominent in biological domains toward applications in detecting endangered or threatened species like Houston toad and Crawfish frog. Researchers at Texas State University and Texas A&M University are working on a project to rescue these species and understanding the causes of their decline. Currently the researchers are using an Automated Recording Device (ARD), Toadphone 1, an embedded solution designed for only Houston toad call detection. However, this device's software solution has shown limited success in identifying toad calls consequent of high false-positive rates. This paper experimented with a modified software solution for existing ARD, which is capable of detecting Houston toad and Crawfish frog calls with decreased false-positive rates. Six experiments to detect the calls were designed by using thirty-nine Mel-Frequency Cepstral Coefficients (MFCCs) with delta and delta-delta coefficients and sixteen Spectral Sub-band Centroids (SSCs) as audio features within Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRUs) as the classifiers. Results show that LSTM as the classifier with thirty-nine MFCCs audio features, and a 20% validation split produces the highest accuracy for detecting Houston toad and Crawfish frog calls. This architecture has gained 84.7% training, 82.05% validation accuracy, and 84.2% test accuracy with 91.4% test accuracy on Houston toad call and 77.1% on Crawfish frog call.","PeriodicalId":433609,"journal":{"name":"2020 11th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133779193","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 : 2020-10-28DOI: 10.1109/UEMCON51285.2020.9298041
Carl Haberfeld, A. Sheta, M. Hossain, H. Turabieh, S. Surani
In this paper, we provide a consistent, inexpensive, and easy to use graphical user interface (GUI) smart phone application named Sleep Apnea Screener (SAS) that can diagnosis Obstructive Sleep Apnea (OSA) based on demographic data such as: gender, age, height, BMI, neck circumference, waist, etc., allowing a tentative diagnosis of OSA without the need for overnight tests. The developed smart phone application can diagnosis sleep apnea using a model trained with 620 samples collected from a sleep center in Corpus Christi, TX. Two machine learning classifiers (i.e., Logistic Regression (LR) and Support Vector Machine (SVM)) were used to diagnosis OSA. Our preliminary results show that at-home OSA screening is indeed possible, and that our application is effective method for covering large numbers of undiagnosed cases.
{"title":"SAS Mobile Application for Diagnosis of Obstructive Sleep Apnea Utilizing Machine Learning Models","authors":"Carl Haberfeld, A. Sheta, M. Hossain, H. Turabieh, S. Surani","doi":"10.1109/UEMCON51285.2020.9298041","DOIUrl":"https://doi.org/10.1109/UEMCON51285.2020.9298041","url":null,"abstract":"In this paper, we provide a consistent, inexpensive, and easy to use graphical user interface (GUI) smart phone application named Sleep Apnea Screener (SAS) that can diagnosis Obstructive Sleep Apnea (OSA) based on demographic data such as: gender, age, height, BMI, neck circumference, waist, etc., allowing a tentative diagnosis of OSA without the need for overnight tests. The developed smart phone application can diagnosis sleep apnea using a model trained with 620 samples collected from a sleep center in Corpus Christi, TX. Two machine learning classifiers (i.e., Logistic Regression (LR) and Support Vector Machine (SVM)) were used to diagnosis OSA. Our preliminary results show that at-home OSA screening is indeed possible, and that our application is effective method for covering large numbers of undiagnosed cases.","PeriodicalId":433609,"journal":{"name":"2020 11th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116786074","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 : 2020-10-28DOI: 10.1109/UEMCON51285.2020.9298135
I. Dutta, Bhaskar Ghosh, Albert H Carlson, Michael W. Totaro, M. Bayoumi
In the Information Age, the majority of data stored and transferred is digital; however, current security systems are not powerful enough to secure this data because they do not anticipate unknown attacks. With a growing number of attacks on cybersecurity systems defense mechanisms need to stay updated with the evolving threats. Security and their related attacks are an iterative pair of objects that learn to enhance themselves based upon each others’ advances – a cybersecurity "arms race." In this survey, we focus on the various ways in which Generative Adversarial Networks (GANs) have been used to provide both security advances and attack scenarios in order to bypass detection systems. The aim of our survey is to examine works completed in the area of GANs, specifically device and network security. This paper also discusses new challenges for intrusion detection systems that have been generated using GANs. Considering the promising results that have been achieved in different GAN applications, it is very likely that GANs can shape security advances if applied to cybersecurity.
{"title":"Generative Adversarial Networks in Security: A Survey","authors":"I. Dutta, Bhaskar Ghosh, Albert H Carlson, Michael W. Totaro, M. Bayoumi","doi":"10.1109/UEMCON51285.2020.9298135","DOIUrl":"https://doi.org/10.1109/UEMCON51285.2020.9298135","url":null,"abstract":"In the Information Age, the majority of data stored and transferred is digital; however, current security systems are not powerful enough to secure this data because they do not anticipate unknown attacks. With a growing number of attacks on cybersecurity systems defense mechanisms need to stay updated with the evolving threats. Security and their related attacks are an iterative pair of objects that learn to enhance themselves based upon each others’ advances – a cybersecurity \"arms race.\" In this survey, we focus on the various ways in which Generative Adversarial Networks (GANs) have been used to provide both security advances and attack scenarios in order to bypass detection systems. The aim of our survey is to examine works completed in the area of GANs, specifically device and network security. This paper also discusses new challenges for intrusion detection systems that have been generated using GANs. Considering the promising results that have been achieved in different GAN applications, it is very likely that GANs can shape security advances if applied to cybersecurity.","PeriodicalId":433609,"journal":{"name":"2020 11th IEEE Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125383898","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：