Pub Date : 2022-11-30DOI: 10.1109/ITNAC55475.2022.9998378
Mohammad Hassan, M. Gregory, Shuo Li
The Software Defined Networking (SDN) paradigm has the potential to improve the operation and efficiency of the global Internet. In recent times, SDN has been extensively adopted in data centres and business networks. Recently, more research is being carried out to find solutions to the problems caused by the continually increasing complexities of the SDN. Issues regarding the lack of transparency between SDN domains impact security, so peer authentication is required. Peer authentication remains a critical issue. SDN domains are linked by the routing protocol Border Gateway Protocol Version 4 (BGP4). To improve the transparency of BGP4 transactions, this paper proposed a Blockchain-based BGP4 Orchestration (BBO) framework that utilises an Internet number resource authority and trustworthy management entity. BBO provides an origin advertisement source and has been found to outperform Resource Public Key Infrastructure (RPKI) in terms of securing origin advertisement and establishing a required setting for the resource repository. This research work ensures sufficient deployment incentives for SDN based federations.
软件定义网络(SDN)范式具有改善全球互联网运行和效率的潜力。近年来，SDN已被广泛应用于数据中心和业务网络中。近年来，人们正在进行更多的研究，以寻找解决SDN不断增加的复杂性所带来的问题。关于SDN域之间缺乏透明度的问题会影响安全性，因此需要对等身份验证。对等身份验证仍然是一个关键问题。SDN域之间通过路由协议BGP4 (Border Gateway protocol Version 4)连接。为了提高BGP4交易的透明度，本文提出了一种基于区块链的BGP4编排(BBO)框架，该框架利用互联网号码资源权威和可信赖的管理实体。BBO提供了一个源发布源，并且在保护源发布和为资源存储库建立所需设置方面优于资源公钥基础设施(Resource Public Key Infrastructure, RPKI)。这项研究工作确保了对基于SDN的联盟有足够的部署激励。
{"title":"Blockchain enhanced BGP4 Security for an SDN based Federation","authors":"Mohammad Hassan, M. Gregory, Shuo Li","doi":"10.1109/ITNAC55475.2022.9998378","DOIUrl":"https://doi.org/10.1109/ITNAC55475.2022.9998378","url":null,"abstract":"The Software Defined Networking (SDN) paradigm has the potential to improve the operation and efficiency of the global Internet. In recent times, SDN has been extensively adopted in data centres and business networks. Recently, more research is being carried out to find solutions to the problems caused by the continually increasing complexities of the SDN. Issues regarding the lack of transparency between SDN domains impact security, so peer authentication is required. Peer authentication remains a critical issue. SDN domains are linked by the routing protocol Border Gateway Protocol Version 4 (BGP4). To improve the transparency of BGP4 transactions, this paper proposed a Blockchain-based BGP4 Orchestration (BBO) framework that utilises an Internet number resource authority and trustworthy management entity. BBO provides an origin advertisement source and has been found to outperform Resource Public Key Infrastructure (RPKI) in terms of securing origin advertisement and establishing a required setting for the resource repository. This research work ensures sufficient deployment incentives for SDN based federations.","PeriodicalId":205731,"journal":{"name":"2022 32nd International Telecommunication Networks and Applications Conference (ITNAC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131314599","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 : 2022-11-30DOI: 10.1109/ITNAC55475.2022.9998393
Farinaz Jowkarishasaltaneh, J. But, A. Cricenti
The MPTCP Transport Layer protocol allows applications to make use of multiple network interfaces simultaneously, allowing for improved throughput and resilience. MPTCP deploys a number of coupled congestion control algorithms that couple congestion window growth across multiple subflows. This restricts window growth to allow competing TCP flows to attain a fair bandwidth share. We examine the performance of existing algorithms across both shared and disjoint paths, finding that these function reasonably only when the bottleneck is shared and the paths exhibit a low bandwidth-delay product. We then propose using uncoupled congestion control within MPTCP, instead managing fairness within the network using SDN. Experimental validation shows that this approach results in fair sharing across shared and disjoint paths, including those with higher bandwidth-delay products.
{"title":"Evaluation of Managing MPTCP Fairness via SDN versus Existing Congestion Control Techniques","authors":"Farinaz Jowkarishasaltaneh, J. But, A. Cricenti","doi":"10.1109/ITNAC55475.2022.9998393","DOIUrl":"https://doi.org/10.1109/ITNAC55475.2022.9998393","url":null,"abstract":"The MPTCP Transport Layer protocol allows applications to make use of multiple network interfaces simultaneously, allowing for improved throughput and resilience. MPTCP deploys a number of coupled congestion control algorithms that couple congestion window growth across multiple subflows. This restricts window growth to allow competing TCP flows to attain a fair bandwidth share. We examine the performance of existing algorithms across both shared and disjoint paths, finding that these function reasonably only when the bottleneck is shared and the paths exhibit a low bandwidth-delay product. We then propose using uncoupled congestion control within MPTCP, instead managing fairness within the network using SDN. Experimental validation shows that this approach results in fair sharing across shared and disjoint paths, including those with higher bandwidth-delay products.","PeriodicalId":205731,"journal":{"name":"2022 32nd International Telecommunication Networks and Applications Conference (ITNAC)","volume":"1232 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133845664","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 : 2022-11-30DOI: 10.1109/ITNAC55475.2022.9998329
Mohammad Yaghoubi, K. Ahmed, Yuan Miao
This study aims to develop a Trust Value Based Intrusion Detection System (TIDS) to identify and prevent Denial of Sleep attacks (DoSL) in Wireless Body Sensor Networks (WBAN). To detect and deter DoSL attacks, this IDS employs pre-distributed random keys, random passwords, the trust value of each node, node energy consumption, and an agent database. Since sending and receiving information packets within the network consumes the energy of the sensors, adopting an appropriate and optimal method to reduce energy consumption and efficient routing selection is necessary. The proposed framework uses Genetic Algorithm (GA) to select the optimal Cluster Head (CH) and the Ad-hoc On-demand Distance Vector (AODV) routing protocol for intra-cluster routing. This work simulates two attack scenarios: one in the presence of IDS and one in its absence, to understand the efficiency and effectiveness of IDS. In both scenarios, we measure and compare various network parameters such as throughput, network lifetime, Packet Delivery Rate (PDR), and node residual energy. We also benchmark TIDS against one of the recent highly cited works, “Secure and energy-efficient framework using Internet of Medical Things (IoMT) for e-healthcare (SEF-IoMT)”, against all network parameters listed above. The simulation results and their comparison with the benchmark study show that the proposed method could significantly improve the network parameters in deterring DoSL attacks. This study uses NS2 for running all tests and experiments.
{"title":"TIDS: Trust Value-Based IDS Framework for Wireless Body Area Network","authors":"Mohammad Yaghoubi, K. Ahmed, Yuan Miao","doi":"10.1109/ITNAC55475.2022.9998329","DOIUrl":"https://doi.org/10.1109/ITNAC55475.2022.9998329","url":null,"abstract":"This study aims to develop a Trust Value Based Intrusion Detection System (TIDS) to identify and prevent Denial of Sleep attacks (DoSL) in Wireless Body Sensor Networks (WBAN). To detect and deter DoSL attacks, this IDS employs pre-distributed random keys, random passwords, the trust value of each node, node energy consumption, and an agent database. Since sending and receiving information packets within the network consumes the energy of the sensors, adopting an appropriate and optimal method to reduce energy consumption and efficient routing selection is necessary. The proposed framework uses Genetic Algorithm (GA) to select the optimal Cluster Head (CH) and the Ad-hoc On-demand Distance Vector (AODV) routing protocol for intra-cluster routing. This work simulates two attack scenarios: one in the presence of IDS and one in its absence, to understand the efficiency and effectiveness of IDS. In both scenarios, we measure and compare various network parameters such as throughput, network lifetime, Packet Delivery Rate (PDR), and node residual energy. We also benchmark TIDS against one of the recent highly cited works, “Secure and energy-efficient framework using Internet of Medical Things (IoMT) for e-healthcare (SEF-IoMT)”, against all network parameters listed above. The simulation results and their comparison with the benchmark study show that the proposed method could significantly improve the network parameters in deterring DoSL attacks. This study uses NS2 for running all tests and experiments.","PeriodicalId":205731,"journal":{"name":"2022 32nd International Telecommunication Networks and Applications Conference (ITNAC)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126187987","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 : 2022-11-30DOI: 10.1109/ITNAC55475.2022.9998380
A.H. Ghorab, M. St-Hilaire
The ongoing demand for deploying Virtual Network Functions (VNFs) in cloud environments is driving the motivation to also deploy and enable Service Function Chaining (SFC). However, deploying SFC in a cloud environment includes multiple subproblems such as implementing an SFC-compatible infrastructure, routing design, placement, and scaling. We believe the deployment of SFC-compatible infrastructures and the routing design issues need further attention as they are fundamental constituents of SFC-enabled cloud environments. In this paper, we present a new flexible SFC framework using a multi-nodes Kubernetes cluster, a Software-Defined Networking (SDN) controller, and an OpenFlow-enabled virtual switch known as Open vSwitch (OvS) to deploy and steer the user traffic to a distributed SFC. We demonstrate the correctness of the proposed SFC framework by monitoring the OvS flow table on Kubernetes worker nodes.
{"title":"SDN-Based Service Function Chaining Framework for Kubernetes Cluster Using OvS","authors":"A.H. Ghorab, M. St-Hilaire","doi":"10.1109/ITNAC55475.2022.9998380","DOIUrl":"https://doi.org/10.1109/ITNAC55475.2022.9998380","url":null,"abstract":"The ongoing demand for deploying Virtual Network Functions (VNFs) in cloud environments is driving the motivation to also deploy and enable Service Function Chaining (SFC). However, deploying SFC in a cloud environment includes multiple subproblems such as implementing an SFC-compatible infrastructure, routing design, placement, and scaling. We believe the deployment of SFC-compatible infrastructures and the routing design issues need further attention as they are fundamental constituents of SFC-enabled cloud environments. In this paper, we present a new flexible SFC framework using a multi-nodes Kubernetes cluster, a Software-Defined Networking (SDN) controller, and an OpenFlow-enabled virtual switch known as Open vSwitch (OvS) to deploy and steer the user traffic to a distributed SFC. We demonstrate the correctness of the proposed SFC framework by monitoring the OvS flow table on Kubernetes worker nodes.","PeriodicalId":205731,"journal":{"name":"2022 32nd International Telecommunication Networks and Applications Conference (ITNAC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123427692","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 : 2022-11-30DOI: 10.1109/ITNAC55475.2022.9998377
Alexander Frömming, L. Häring, A. Czylwik
A multicarrier transmission system with clipping distortion on the transmitting side, additive white Gaussian noise on the receiving side and a frequency-selective channel is considered with respect to adaptive modulation. The investigations are made based on an optical intensity modulated band-limited DC-offset orthogonal frequency-division multiplexing (DCO-OFDM) system. Usually, the frequency-selective channel transfer function determines the bit allocation. In the present scenario, this approach must be adapted, because the clipping noise is distorted by the same channel as the information signal. Therefore, adaptive modulation can no longer achieve a gain when clipping becomes the dominating source of distortion. In this paper, the total signal-to-interference-and-noise power ratio (SINR), considering clipping noise at the transmitter and additive noise at the receiver, is calculated. Based on this result, the optimal bit allocation table (BAT) for each scenario, ranging from no clipping to very strong clipping, can be determined. It is shown that the error probability of a band-limited DCO-OFDM transmission can be approximately halved based on this concept. Additionally, the optimal transmit power to achieve the lowest error probability in a given system can be theoretically calculated. The results are verified by simulations.
{"title":"Optimizing Adaptive Modulation for Symmetrically Clipped Band-Limited DCO-OFDM","authors":"Alexander Frömming, L. Häring, A. Czylwik","doi":"10.1109/ITNAC55475.2022.9998377","DOIUrl":"https://doi.org/10.1109/ITNAC55475.2022.9998377","url":null,"abstract":"A multicarrier transmission system with clipping distortion on the transmitting side, additive white Gaussian noise on the receiving side and a frequency-selective channel is considered with respect to adaptive modulation. The investigations are made based on an optical intensity modulated band-limited DC-offset orthogonal frequency-division multiplexing (DCO-OFDM) system. Usually, the frequency-selective channel transfer function determines the bit allocation. In the present scenario, this approach must be adapted, because the clipping noise is distorted by the same channel as the information signal. Therefore, adaptive modulation can no longer achieve a gain when clipping becomes the dominating source of distortion. In this paper, the total signal-to-interference-and-noise power ratio (SINR), considering clipping noise at the transmitter and additive noise at the receiver, is calculated. Based on this result, the optimal bit allocation table (BAT) for each scenario, ranging from no clipping to very strong clipping, can be determined. It is shown that the error probability of a band-limited DCO-OFDM transmission can be approximately halved based on this concept. Additionally, the optimal transmit power to achieve the lowest error probability in a given system can be theoretically calculated. The results are verified by simulations.","PeriodicalId":205731,"journal":{"name":"2022 32nd International Telecommunication Networks and Applications Conference (ITNAC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130571394","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 : 2022-11-30DOI: 10.1109/ITNAC55475.2022.9998410
Don Barber, V. Kanth, Zachary White, J. McEachen
Preventing the exfiltration of critical data via out-of-band channels is one of the most difficult challenges in cybersecurity. This challenge notably includes commu-nications utilizing optical channels. Numerous papers have suggested the modulation of indicator lights to transmit information out of otherwise secure networks. These means of optically embedding data are both challenging to detect and a threat to the security of confidential data. This paper presents a scalable, near-real-time process to detect and localize data hidden in optical channels amid other optical modulation, including electric network frequencies. Assumptions on the detectability of hidden optical channels are reviewed and a method of detecting and localizing transmissions based on spectral artifacts of embedded data is developed. Proof-of-concept experiments demonstrate the successful detection of potential optical data leaks in an office environment. This capability can allow for low cost optical bug sweeping devices, arming information security teams with a tool to detect and mitigate the insidious threat of optical out-of-band channels.
{"title":"Spatial Frequency Detection of Optical Signals Embedded in the Environment","authors":"Don Barber, V. Kanth, Zachary White, J. McEachen","doi":"10.1109/ITNAC55475.2022.9998410","DOIUrl":"https://doi.org/10.1109/ITNAC55475.2022.9998410","url":null,"abstract":"Preventing the exfiltration of critical data via out-of-band channels is one of the most difficult challenges in cybersecurity. This challenge notably includes commu-nications utilizing optical channels. Numerous papers have suggested the modulation of indicator lights to transmit information out of otherwise secure networks. These means of optically embedding data are both challenging to detect and a threat to the security of confidential data. This paper presents a scalable, near-real-time process to detect and localize data hidden in optical channels amid other optical modulation, including electric network frequencies. Assumptions on the detectability of hidden optical channels are reviewed and a method of detecting and localizing transmissions based on spectral artifacts of embedded data is developed. Proof-of-concept experiments demonstrate the successful detection of potential optical data leaks in an office environment. This capability can allow for low cost optical bug sweeping devices, arming information security teams with a tool to detect and mitigate the insidious threat of optical out-of-band channels.","PeriodicalId":205731,"journal":{"name":"2022 32nd International Telecommunication Networks and Applications Conference (ITNAC)","volume":"429 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126088961","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 : 2022-11-30DOI: 10.1109/ITNAC55475.2022.9998387
Keisuke Kobayashi, Toshiro Nunome
This paper considers video and audio transmission in ICN (Information-Centric Networking) CCN (Content- Centric Networking), in which each intermediate node can cache content. LCE (Leave Copy Everywhere) has been known as a generic cache decision policy. However, because LCE caches at all the intermediate nodes, the cache of intermediate nodes can be duplicated. Therefore, various cache decision policies that eliminate redundancy have been proposed. In this paper, we evaluate the effect of the cache decision policies on QoE of video and audio transmission in ICN/CCN. We assess application-level QoS using a computer simulation with a tree network and QoE by means of subjective experiment.
{"title":"The Impact of ICN/CCN Cache Decision Policies on Video and Audio Transmission QoE","authors":"Keisuke Kobayashi, Toshiro Nunome","doi":"10.1109/ITNAC55475.2022.9998387","DOIUrl":"https://doi.org/10.1109/ITNAC55475.2022.9998387","url":null,"abstract":"This paper considers video and audio transmission in ICN (Information-Centric Networking) CCN (Content- Centric Networking), in which each intermediate node can cache content. LCE (Leave Copy Everywhere) has been known as a generic cache decision policy. However, because LCE caches at all the intermediate nodes, the cache of intermediate nodes can be duplicated. Therefore, various cache decision policies that eliminate redundancy have been proposed. In this paper, we evaluate the effect of the cache decision policies on QoE of video and audio transmission in ICN/CCN. We assess application-level QoS using a computer simulation with a tree network and QoE by means of subjective experiment.","PeriodicalId":205731,"journal":{"name":"2022 32nd International Telecommunication Networks and Applications Conference (ITNAC)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125703635","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 : 2022-11-30DOI: 10.1109/ITNAC55475.2022.9998385
Eman Ebaid, K. Navaie
Wi-Fi fingerprinting techniques are commonly used in Indoor Positioning Systems (IPS) as Wi-Fi signal is available in most indoor settings. In such systems, the position is estimated based on a matching algorithm between the enquiry points and the recorded fingerprint data. In this paper, our objective is to investigate and provide quantitative insight into the performance of various Nearest Neighbour (NN) algorithms. The NN algorithms such as KNN are also often employed in IPS. We extensively study the performance of several NN algorithms on a publicly available dataset, UJIIndoorLoc. Furthermore, we propose an improved version of the Weighted KNN algorithm. The proposed model outperforms the existing works on the UJIIndoorLoc dataset and achieves better results for the success rate and the mean positioning error.
{"title":"Optimum NN Algorithms Parameters on the UJIIndoorLoc for Wi-Fi Fingerprinting Indoor Positioning Systems","authors":"Eman Ebaid, K. Navaie","doi":"10.1109/ITNAC55475.2022.9998385","DOIUrl":"https://doi.org/10.1109/ITNAC55475.2022.9998385","url":null,"abstract":"Wi-Fi fingerprinting techniques are commonly used in Indoor Positioning Systems (IPS) as Wi-Fi signal is available in most indoor settings. In such systems, the position is estimated based on a matching algorithm between the enquiry points and the recorded fingerprint data. In this paper, our objective is to investigate and provide quantitative insight into the performance of various Nearest Neighbour (NN) algorithms. The NN algorithms such as KNN are also often employed in IPS. We extensively study the performance of several NN algorithms on a publicly available dataset, UJIIndoorLoc. Furthermore, we propose an improved version of the Weighted KNN algorithm. The proposed model outperforms the existing works on the UJIIndoorLoc dataset and achieves better results for the success rate and the mean positioning error.","PeriodicalId":205731,"journal":{"name":"2022 32nd International Telecommunication Networks and Applications Conference (ITNAC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128809990","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 : 2022-11-30DOI: 10.1109/ITNAC55475.2022.9998390
Dongsheng Zheng, Zijiang Zhou, Wenyao Li, B. Jiao
Improving the bit error rate (BER) performance of finite-length block code is required in the scenarios of ultra-reliable and low latency communications. Nonetheless, the complexity of algorithms to find such a high performance block code increases dramatically as blocklength increases. Towards this end, the paper proposes a low-complexity recursive algorithm to search the optimal binary block codes subject to the requirement of the minimum Hamming distance. As a result, two optimal code sets of code-length 16 and 32 are found with code rate of 1/2. The simulation results show that the constructed codes under binary phase shift keying (BPSK) modulation outperform the systematic polar codes in the same blocklength in terms of the BER performance.
{"title":"A Low-Complexity Approach for Constructing the Optimal Binary Finite-Length Block Code","authors":"Dongsheng Zheng, Zijiang Zhou, Wenyao Li, B. Jiao","doi":"10.1109/ITNAC55475.2022.9998390","DOIUrl":"https://doi.org/10.1109/ITNAC55475.2022.9998390","url":null,"abstract":"Improving the bit error rate (BER) performance of finite-length block code is required in the scenarios of ultra-reliable and low latency communications. Nonetheless, the complexity of algorithms to find such a high performance block code increases dramatically as blocklength increases. Towards this end, the paper proposes a low-complexity recursive algorithm to search the optimal binary block codes subject to the requirement of the minimum Hamming distance. As a result, two optimal code sets of code-length 16 and 32 are found with code rate of 1/2. The simulation results show that the constructed codes under binary phase shift keying (BPSK) modulation outperform the systematic polar codes in the same blocklength in terms of the BER performance.","PeriodicalId":205731,"journal":{"name":"2022 32nd International Telecommunication Networks and Applications Conference (ITNAC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128833705","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 : 2022-11-30DOI: 10.1109/ITNAC55475.2022.9998375
Z. Liu, Ruoyu Wang, Bitao Peng, Qingqing Gan
Android malware detection is an important foundation for guaranteeing the security of Android ecosystem. Convolutional neural network has been applied in Android malware detection. It usually requires a large amount of training samples for building an efficient model. However, the malware data collection costs much time and resources. The lack of training samples may lead to overfitting problem. In addition, the model may become ineffective when the data distribution is significantly changed. To handle these problems, this paper proposes a new malware detection method. It firstly trains a model on an initial training set using convolutional neural network. With the upcoming of more samples, the model is updated by fine-tuning the pre-trained model on the newly labeled data. So that the pre-trained model could be dynamically updated. The experiments on the real datasets show that our method can further improve the accuracy and gmean about 1.3% and 2.4% respectively on average.
{"title":"A convolutional neural network based Android malware detection method with dynamic fine-tuning","authors":"Z. Liu, Ruoyu Wang, Bitao Peng, Qingqing Gan","doi":"10.1109/ITNAC55475.2022.9998375","DOIUrl":"https://doi.org/10.1109/ITNAC55475.2022.9998375","url":null,"abstract":"Android malware detection is an important foundation for guaranteeing the security of Android ecosystem. Convolutional neural network has been applied in Android malware detection. It usually requires a large amount of training samples for building an efficient model. However, the malware data collection costs much time and resources. The lack of training samples may lead to overfitting problem. In addition, the model may become ineffective when the data distribution is significantly changed. To handle these problems, this paper proposes a new malware detection method. It firstly trains a model on an initial training set using convolutional neural network. With the upcoming of more samples, the model is updated by fine-tuning the pre-trained model on the newly labeled data. So that the pre-trained model could be dynamically updated. The experiments on the real datasets show that our method can further improve the accuracy and gmean about 1.3% and 2.4% respectively on average.","PeriodicalId":205731,"journal":{"name":"2022 32nd International Telecommunication Networks and Applications Conference (ITNAC)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116396626","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：