Pub Date : 2022-06-01DOI: 10.1109/wowmom54355.2022.00098
{"title":"Message from the Joint Workshop Chairs","authors":"","doi":"10.1109/wowmom54355.2022.00098","DOIUrl":"https://doi.org/10.1109/wowmom54355.2022.00098","url":null,"abstract":"","PeriodicalId":275324,"journal":{"name":"2022 IEEE 23rd International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129608058","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 : 2022-06-01DOI: 10.1109/wowmom54355.2022.00011
{"title":"Reviewers: NTN-6G 2022","authors":"","doi":"10.1109/wowmom54355.2022.00011","DOIUrl":"https://doi.org/10.1109/wowmom54355.2022.00011","url":null,"abstract":"","PeriodicalId":275324,"journal":{"name":"2022 IEEE 23rd International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM)","volume":"295 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120947947","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 : 2022-06-01DOI: 10.1109/WoWMoM54355.2022.00040
Corentin Fonteneau, M. Crussiére, B. Jahan
Millimeter wave communication systems define a new paradigm for wireless communications. At such high frequencies, multi-input multi-output (MIMO) processing is done on the radio-frequency signals to limit the hardware complexity and the energy consumption. Consequently, the channel experienced by the receiver directly depends on the transmitter and receiver antenna array responses, making the determination of the analog precoder and combiner an intertwined problem. In this paper, we propose a procedure capable of calculating analog weights at the transmitter and at the receiver, which allows the maximization of the wideband spectral efficiency for single stream transmission single user MIMO (SU-MIMO). While solely relying on partial channel state information (CSI), our procedure has close performance to full CSI-dependent schemes.
{"title":"An Efficient Analog Eigen-Beamforming Procedure for Wideband mmWave MIMO-OFDM Systems","authors":"Corentin Fonteneau, M. Crussiére, B. Jahan","doi":"10.1109/WoWMoM54355.2022.00040","DOIUrl":"https://doi.org/10.1109/WoWMoM54355.2022.00040","url":null,"abstract":"Millimeter wave communication systems define a new paradigm for wireless communications. At such high frequencies, multi-input multi-output (MIMO) processing is done on the radio-frequency signals to limit the hardware complexity and the energy consumption. Consequently, the channel experienced by the receiver directly depends on the transmitter and receiver antenna array responses, making the determination of the analog precoder and combiner an intertwined problem. In this paper, we propose a procedure capable of calculating analog weights at the transmitter and at the receiver, which allows the maximization of the wideband spectral efficiency for single stream transmission single user MIMO (SU-MIMO). While solely relying on partial channel state information (CSI), our procedure has close performance to full CSI-dependent schemes.","PeriodicalId":275324,"journal":{"name":"2022 IEEE 23rd International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114310445","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 : 2022-06-01DOI: 10.1109/WoWMoM54355.2022.00079
D. Garg, Neeraj Kumar, Nazeeruddin Mohammad
Smart grids are an improvement of the traditional electric grids. They allow a much higher degree of automation and more efficient power distribution. Nonetheless, due to automation, these grids become more vulnerable to cyber attacks. Hence, cyber security becomes a major milestone to overcome before we can permanently shift to smart grids. Electric theft is one of the most dangerous cyber attacks in a smart grid. It allows users to lie about their load profiles and decrease their electricity bills. Several research studies have been conducted regarding the detection of such cyber attacks in a smart grid, but none of them consider weather information as a feature. This paper proposes a novel machine learning-based approach to smart grid electricity theft detection using both the load profile of a household and the weather features. The results show that our current approach using both load and weather information perform much better than previous approaches that only use load information.
{"title":"An Intelligent Machine Learning Approach for Smart Grid Theft Detection","authors":"D. Garg, Neeraj Kumar, Nazeeruddin Mohammad","doi":"10.1109/WoWMoM54355.2022.00079","DOIUrl":"https://doi.org/10.1109/WoWMoM54355.2022.00079","url":null,"abstract":"Smart grids are an improvement of the traditional electric grids. They allow a much higher degree of automation and more efficient power distribution. Nonetheless, due to automation, these grids become more vulnerable to cyber attacks. Hence, cyber security becomes a major milestone to overcome before we can permanently shift to smart grids. Electric theft is one of the most dangerous cyber attacks in a smart grid. It allows users to lie about their load profiles and decrease their electricity bills. Several research studies have been conducted regarding the detection of such cyber attacks in a smart grid, but none of them consider weather information as a feature. This paper proposes a novel machine learning-based approach to smart grid electricity theft detection using both the load profile of a household and the weather features. The results show that our current approach using both load and weather information perform much better than previous approaches that only use load information.","PeriodicalId":275324,"journal":{"name":"2022 IEEE 23rd International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130259922","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 : 2022-06-01DOI: 10.1109/WoWMoM54355.2022.00080
K. Chen, Shuyi Wang, Haotong Cao
With the continuous development of social science and technology, artificial intelligence identification has been widely used and plays a very important role in some special fields. Convolutional neural network has a good effect in image processing, so it is widely used in intelligent recognition scenario. Activation functions can help convolutional neural network better understand and fit complex function models, It is necessary to design an efficient activation function. This paper proposes a new convolutional neural network model based on improved activation function usage patterns, and the performances of three common used activation functions, including sigmoid function, tanh function and relu function, in centralized and decentralized training methods are detailed analyzed respectively. The experiment results show that the effect of repeated training with different activation functions is better than that of single linear rectification function in recognition accuracy and recognition of special cases, and the recognition speed is obviously faster than the traditional model. Furthermore, under the same activation function, when the number of training rounds and the training amount are small, the expected accuracy of centralized training is lower compared with that of decentralized training, but the detection accuracy is improved due to the detection mechanism.
{"title":"A New Artificial Intelligence Recognition Technology Based On Convolutional Neural Networks","authors":"K. Chen, Shuyi Wang, Haotong Cao","doi":"10.1109/WoWMoM54355.2022.00080","DOIUrl":"https://doi.org/10.1109/WoWMoM54355.2022.00080","url":null,"abstract":"With the continuous development of social science and technology, artificial intelligence identification has been widely used and plays a very important role in some special fields. Convolutional neural network has a good effect in image processing, so it is widely used in intelligent recognition scenario. Activation functions can help convolutional neural network better understand and fit complex function models, It is necessary to design an efficient activation function. This paper proposes a new convolutional neural network model based on improved activation function usage patterns, and the performances of three common used activation functions, including sigmoid function, tanh function and relu function, in centralized and decentralized training methods are detailed analyzed respectively. The experiment results show that the effect of repeated training with different activation functions is better than that of single linear rectification function in recognition accuracy and recognition of special cases, and the recognition speed is obviously faster than the traditional model. Furthermore, under the same activation function, when the number of training rounds and the training amount are small, the expected accuracy of centralized training is lower compared with that of decentralized training, but the detection accuracy is improved due to the detection mechanism.","PeriodicalId":275324,"journal":{"name":"2022 IEEE 23rd International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133977866","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}
5G mmWave is being rapidly deployed by all major mobile operators. With the technology still in its infancy, several early research works analyze the performance of operational 5G mmWave networks. Nonetheless, these measurement studies primarily focus on single-user performance, leaving the sharing and resource allocation policies largely unexplored. In this paper, we fill this gap by conducting the, to our best knowledge, first systematic study of resource allocation policies of current 5G mmWave mobile network deployments through an extensive measurement campaign across four major US cities and two major mobile operators. Our study reveals that resource allocation among multiple flows is strictly governed by the cellular operators and flows are not allowed to compete with each other in a shared queue. Operators employ simple threshold-based policies and often over-allocate resources to new flows with low traffic demands or reserve some capacity for future usage. Interestingly, these policies vary not only among operators but also for a single operator in different cities. We also discuss a number of anomalous behaviors we observed in our experiments across different cities and operators.
{"title":"Demystifying Resource Allocation Policies in Operational 5G mmWave Networks","authors":"Phuc Dinh, Moinak Ghoshal, Dimitrios Koutsonikolas, Joerg Widmer","doi":"10.1109/WoWMoM54355.2022.00016","DOIUrl":"https://doi.org/10.1109/WoWMoM54355.2022.00016","url":null,"abstract":"5G mmWave is being rapidly deployed by all major mobile operators. With the technology still in its infancy, several early research works analyze the performance of operational 5G mmWave networks. Nonetheless, these measurement studies primarily focus on single-user performance, leaving the sharing and resource allocation policies largely unexplored. In this paper, we fill this gap by conducting the, to our best knowledge, first systematic study of resource allocation policies of current 5G mmWave mobile network deployments through an extensive measurement campaign across four major US cities and two major mobile operators. Our study reveals that resource allocation among multiple flows is strictly governed by the cellular operators and flows are not allowed to compete with each other in a shared queue. Operators employ simple threshold-based policies and often over-allocate resources to new flows with low traffic demands or reserve some capacity for future usage. Interestingly, these policies vary not only among operators but also for a single operator in different cities. We also discuss a number of anomalous behaviors we observed in our experiments across different cities and operators.","PeriodicalId":275324,"journal":{"name":"2022 IEEE 23rd International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134472745","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 : 2022-06-01DOI: 10.1109/WoWMoM54355.2022.00064
Qing Guo, Linfu Xie, Xinran Lu, Baoliu Ye, Sanglu Lu
In industrial production, the orientation of facility is a powerful indicator to verify whether the facility is in a normal operating track. In this paper, we present LightGyro, a cheap and efficient batteryless scheme to measure the facility orientation, it leverages the orientation amplification effect of reflection to improve the measuring accuracy to one degree. LightGyro system is composed of low-cost camera, batteryless reflective film and LEDs. In the working process of LightGyro, we attach a reflective film to the target and let it reflect the light from LEDs to the camera. Then the LightGyro would extract the LED-related spots in the captured frame and restore the reflection route to measure the orientation. To extract the LED-related spots from complicated background automatically, we propose to leverage the affine transformation to search for the topology of multiple spots which is related to the deployed LED array. To address the dimension missing issue caused by camera projection and restore the reflection route, we propose a light array-based reflection model to extract the missing dimension from relative positions of multiple spots. To the best of our knowledge, this is the first work to utilize light reflection to measure orientation. Our experiments show that the average accuracy of LightGyro achieves less than 2◦. When the reflective film is far from the camera, the mean error is less than 1◦.
{"title":"LightGyro:A Light-based Orientation Measuring Scheme Using Batteryless Reflective Film","authors":"Qing Guo, Linfu Xie, Xinran Lu, Baoliu Ye, Sanglu Lu","doi":"10.1109/WoWMoM54355.2022.00064","DOIUrl":"https://doi.org/10.1109/WoWMoM54355.2022.00064","url":null,"abstract":"In industrial production, the orientation of facility is a powerful indicator to verify whether the facility is in a normal operating track. In this paper, we present LightGyro, a cheap and efficient batteryless scheme to measure the facility orientation, it leverages the orientation amplification effect of reflection to improve the measuring accuracy to one degree. LightGyro system is composed of low-cost camera, batteryless reflective film and LEDs. In the working process of LightGyro, we attach a reflective film to the target and let it reflect the light from LEDs to the camera. Then the LightGyro would extract the LED-related spots in the captured frame and restore the reflection route to measure the orientation. To extract the LED-related spots from complicated background automatically, we propose to leverage the affine transformation to search for the topology of multiple spots which is related to the deployed LED array. To address the dimension missing issue caused by camera projection and restore the reflection route, we propose a light array-based reflection model to extract the missing dimension from relative positions of multiple spots. To the best of our knowledge, this is the first work to utilize light reflection to measure orientation. Our experiments show that the average accuracy of LightGyro achieves less than 2◦. When the reflective film is far from the camera, the mean error is less than 1◦.","PeriodicalId":275324,"journal":{"name":"2022 IEEE 23rd International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125817553","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 : 2022-06-01DOI: 10.1109/WoWMoM54355.2022.00031
Koustabh Dolui, Sam Michiels, D. Hughes, H. Hallez
With the emergence of mobile devices having enough resources to execute real-time ML inference, deployment opportunities arise on mobile devices while keeping privacy-sensitive data close to the source and reducing server load. Moreover, offloading inference to a cloud server facilitates deployment of neural network-based applications on resource-constrained devices. Depending on the application goals and execution context of the application, the optimal deployment on either cloud server or mobile device varies during the lifetime of an application. In this paper, we propose a context-aware middleware that enables optimization of deployed application software to satisfy the application’s functional goals in accordance with changing execution context and environmental conditions. We facilitate system design through the abstraction of deployed software components as states and make use of finite state machines and contextual triggers to model the reconfiguration of the system. We evaluate our framework using a real-world nutritional monitoring application via food image recognition deployed in a two-tier mobile and cloud architecture. We compare the proposed solution with various static deployments of the application and show that our approach can react to changing application goals at run-time in order to reduce server load and thereby increase scalability.
{"title":"Context Aware Adaptive ML Inference in Mobile-Cloud Applications","authors":"Koustabh Dolui, Sam Michiels, D. Hughes, H. Hallez","doi":"10.1109/WoWMoM54355.2022.00031","DOIUrl":"https://doi.org/10.1109/WoWMoM54355.2022.00031","url":null,"abstract":"With the emergence of mobile devices having enough resources to execute real-time ML inference, deployment opportunities arise on mobile devices while keeping privacy-sensitive data close to the source and reducing server load. Moreover, offloading inference to a cloud server facilitates deployment of neural network-based applications on resource-constrained devices. Depending on the application goals and execution context of the application, the optimal deployment on either cloud server or mobile device varies during the lifetime of an application. In this paper, we propose a context-aware middleware that enables optimization of deployed application software to satisfy the application’s functional goals in accordance with changing execution context and environmental conditions. We facilitate system design through the abstraction of deployed software components as states and make use of finite state machines and contextual triggers to model the reconfiguration of the system. We evaluate our framework using a real-world nutritional monitoring application via food image recognition deployed in a two-tier mobile and cloud architecture. We compare the proposed solution with various static deployments of the application and show that our approach can react to changing application goals at run-time in order to reduce server load and thereby increase scalability.","PeriodicalId":275324,"journal":{"name":"2022 IEEE 23rd International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127463223","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 : 2022-06-01DOI: 10.1109/WoWMoM54355.2022.00055
Cong Wang, Xiaohan Li, M. Ma, Yiying Zhang
In a smart grid, the identity authentication between a smart meter and an aggregator is a prerequisite for both parties to establish a secure channel. All existing authentication schemes have their own shortcomings in either security or efficiency to make them difficult to meet the security requirements of the smart grid. In this paper, we are motivated to propose an efficient and secure mutual authentication scheme based on the extended Chebyshev chaotic maps. The smart meters and aggregators are registered with a trusted third party to conduct a mutual authentication. The proposed scheme provides anonymity protection for smart meters to achieve perfect forward secrecy. Through security analysis, we conclude that the proposed scheme has the characteristics of high security. In addition, we compare the proposed scheme with other three schemes in terms of number of encryption operations, computation delay. The performance comparison demonstrates that the proposed scheme is efficient without sacrificing the desired security properties.
{"title":"A Novel and Efficient Anonymous Authentication Scheme Based on Extended Chebyshev Chaotic Maps for Smart Grid","authors":"Cong Wang, Xiaohan Li, M. Ma, Yiying Zhang","doi":"10.1109/WoWMoM54355.2022.00055","DOIUrl":"https://doi.org/10.1109/WoWMoM54355.2022.00055","url":null,"abstract":"In a smart grid, the identity authentication between a smart meter and an aggregator is a prerequisite for both parties to establish a secure channel. All existing authentication schemes have their own shortcomings in either security or efficiency to make them difficult to meet the security requirements of the smart grid. In this paper, we are motivated to propose an efficient and secure mutual authentication scheme based on the extended Chebyshev chaotic maps. The smart meters and aggregators are registered with a trusted third party to conduct a mutual authentication. The proposed scheme provides anonymity protection for smart meters to achieve perfect forward secrecy. Through security analysis, we conclude that the proposed scheme has the characteristics of high security. In addition, we compare the proposed scheme with other three schemes in terms of number of encryption operations, computation delay. The performance comparison demonstrates that the proposed scheme is efficient without sacrificing the desired security properties.","PeriodicalId":275324,"journal":{"name":"2022 IEEE 23rd International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121308266","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 : 2022-06-01DOI: 10.1109/WoWMoM54355.2022.00081
Arman Pashamokhtari, Arunan Sivanathan, Ayyoob Hamza, H. Gharakheili
The Manufacturer Usage Description (MUD) standard aims to reduce the attack surface for IoT devices by locking down their behavior to a formally-specified set of network flows (access control entries). Formal network behaviors can also be systematically and rigorously verified in any operating environment. Enforcing MUD flows and monitoring their activity in real-time can be relatively effective in securing IoT devices; however, its scope is limited to endpoints (domain names and IP addresses) and transport-layer protocols and services. Therefore, misconfigured or compromised IoTs may conform to their MUD-specified behavior but exchange unintended (or even malicious) contents across those flows. This paper develops PicP-MUD with the aim to profile the information content of packet payloads (whether unencrypted, encoded, or encrypted) in each MUD flow of an IoT device. That way, certain tasks like cyber-risk analysis, change detection, or selective deep packet inspection can be performed in a more systematic manner. Our contributions are twofold: (1) We analyze over 123K network flows of 6 transparent (e.g., HTTP), 11 encrypted (e.g., TLS), and 7 encoded (e.g., RTP) protocols, collected in our lab and obtained from public datasets, to identify 17 statistical features of their application payload, helping us distinguish different content types; and (2) We develop and evaluate PicP-MUD using a machine learning model, and show how we achieve an average accuracy of 99% in predicting the content type of a flow.
{"title":"PicP-MUD: Profiling Information Content of Payloads in MUD Flows for IoT Devices","authors":"Arman Pashamokhtari, Arunan Sivanathan, Ayyoob Hamza, H. Gharakheili","doi":"10.1109/WoWMoM54355.2022.00081","DOIUrl":"https://doi.org/10.1109/WoWMoM54355.2022.00081","url":null,"abstract":"The Manufacturer Usage Description (MUD) standard aims to reduce the attack surface for IoT devices by locking down their behavior to a formally-specified set of network flows (access control entries). Formal network behaviors can also be systematically and rigorously verified in any operating environment. Enforcing MUD flows and monitoring their activity in real-time can be relatively effective in securing IoT devices; however, its scope is limited to endpoints (domain names and IP addresses) and transport-layer protocols and services. Therefore, misconfigured or compromised IoTs may conform to their MUD-specified behavior but exchange unintended (or even malicious) contents across those flows. This paper develops PicP-MUD with the aim to profile the information content of packet payloads (whether unencrypted, encoded, or encrypted) in each MUD flow of an IoT device. That way, certain tasks like cyber-risk analysis, change detection, or selective deep packet inspection can be performed in a more systematic manner. Our contributions are twofold: (1) We analyze over 123K network flows of 6 transparent (e.g., HTTP), 11 encrypted (e.g., TLS), and 7 encoded (e.g., RTP) protocols, collected in our lab and obtained from public datasets, to identify 17 statistical features of their application payload, helping us distinguish different content types; and (2) We develop and evaluate PicP-MUD using a machine learning model, and show how we achieve an average accuracy of 99% in predicting the content type of a flow.","PeriodicalId":275324,"journal":{"name":"2022 IEEE 23rd International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM)","volume":"345 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116657898","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：