Samuel Bair, Matthew DelVecchio, Bryse Flowers, Alan J. Michaels, W. Headley
Wireless communications has greatly benefited in recent years from advances in machine learning. A new subfield, commonly termed Radio Frequency Machine Learning (RFML), has emerged that has demonstrated the application of Deep Neural Networks to multiple spectrum sensing tasks such as modulation recognition and specific emitter identification. Yet, recent research in the RF domain has shown that these models are vulnerable to over-the-air adversarial evasion attacks, which seek to cause minimum harm to the underlying transmission to a cooperative receiver, while greatly lowering the performance of spectrum sensing tasks by an eavesdropper. While prior work has focused on untargeted evasion, which simply degrades classification accuracy, this paper focuses on targeted evasion attacks, which aim to masquerade as a specific signal of interest. The current work examines how a Convolutional Neural Network (CNN) based Automatic Modulation Classification (AMC) model breaks down in the presence of an adversary with direct access to its inputs. Specifically, the current work uses the adversarial perturbation power needed to change the classification from a specific source modulation to a specific target modulation as a proxy for the model's estimation of their similarity and compares this with the known hierarchy of these human engineered modulations. The findings conclude that the reference model breaks down in an intuitive way, which can have implications on progress towards hardening RFML models.
{"title":"On the Limitations of Targeted Adversarial Evasion Attacks Against Deep Learning Enabled Modulation Recognition","authors":"Samuel Bair, Matthew DelVecchio, Bryse Flowers, Alan J. Michaels, W. Headley","doi":"10.1145/3324921.3328785","DOIUrl":"https://doi.org/10.1145/3324921.3328785","url":null,"abstract":"Wireless communications has greatly benefited in recent years from advances in machine learning. A new subfield, commonly termed Radio Frequency Machine Learning (RFML), has emerged that has demonstrated the application of Deep Neural Networks to multiple spectrum sensing tasks such as modulation recognition and specific emitter identification. Yet, recent research in the RF domain has shown that these models are vulnerable to over-the-air adversarial evasion attacks, which seek to cause minimum harm to the underlying transmission to a cooperative receiver, while greatly lowering the performance of spectrum sensing tasks by an eavesdropper. While prior work has focused on untargeted evasion, which simply degrades classification accuracy, this paper focuses on targeted evasion attacks, which aim to masquerade as a specific signal of interest. The current work examines how a Convolutional Neural Network (CNN) based Automatic Modulation Classification (AMC) model breaks down in the presence of an adversary with direct access to its inputs. Specifically, the current work uses the adversarial perturbation power needed to change the classification from a specific source modulation to a specific target modulation as a proxy for the model's estimation of their similarity and compares this with the known hierarchy of these human engineered modulations. The findings conclude that the reference model breaks down in an intuitive way, which can have implications on progress towards hardening RFML models.","PeriodicalId":435733,"journal":{"name":"Proceedings of the ACM Workshop on Wireless Security and Machine Learning","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133893318","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}
Wireless Virtualization (WiVi) is emerging as a new paradigm to provide high speed communications and meet Quality-of-Service (QoS) requirements of users while reducing the deployment cost of wireless infrastructure for future wireless networks. In WiVi, Wireless Infrastructure Providers (WIPs) sublease their RF channels through slicing to Mobile Virtual Network Operators (MVNOs) based on their Service Level Agreements (SLAs) and the MVNOs independently provide wireless services to their end users. This paper investigates the wireless network virtualization by leveraging both Blockchain technology and machine learning to optimally allocate wireless resources. To eliminate double spending (aka over-committing) of WIPs' wireless resources such as RF channels, Blockchain - a distributed ledger - technology is used where a reputation is used to penalize WIPs with past double spending habit. The proposed reputation based approach helps to minimize extra delay caused by double spending attempts and Blockchain operations. To optimally predict the QoS requirements of MVNOs for their users, linear regression - a machine learning approach - is used that helps to minimize the latency introduced due to (multiple wrong) negotiations for SLAs. The performance evaluation of the proposed approach is carried out by using numerical results obtained from simulations. Results have shown that the joint Blockchain and machine learning based approach outperforms the other approaches.
{"title":"Wireless Network Virtualization by Leveraging Blockchain Technology and Machine Learning","authors":"Ashish Adhikari, D. Rawat, Min Song","doi":"10.1145/3324921.3328790","DOIUrl":"https://doi.org/10.1145/3324921.3328790","url":null,"abstract":"Wireless Virtualization (WiVi) is emerging as a new paradigm to provide high speed communications and meet Quality-of-Service (QoS) requirements of users while reducing the deployment cost of wireless infrastructure for future wireless networks. In WiVi, Wireless Infrastructure Providers (WIPs) sublease their RF channels through slicing to Mobile Virtual Network Operators (MVNOs) based on their Service Level Agreements (SLAs) and the MVNOs independently provide wireless services to their end users. This paper investigates the wireless network virtualization by leveraging both Blockchain technology and machine learning to optimally allocate wireless resources. To eliminate double spending (aka over-committing) of WIPs' wireless resources such as RF channels, Blockchain - a distributed ledger - technology is used where a reputation is used to penalize WIPs with past double spending habit. The proposed reputation based approach helps to minimize extra delay caused by double spending attempts and Blockchain operations. To optimally predict the QoS requirements of MVNOs for their users, linear regression - a machine learning approach - is used that helps to minimize the latency introduced due to (multiple wrong) negotiations for SLAs. The performance evaluation of the proposed approach is carried out by using numerical results obtained from simulations. Results have shown that the joint Blockchain and machine learning based approach outperforms the other approaches.","PeriodicalId":435733,"journal":{"name":"Proceedings of the ACM Workshop on Wireless Security and Machine Learning","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131721576","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}
Zachary L. Langford, Logan Eisenbeiser, Matthew Vondal
We propose a noise-robust signal classification approach using siamese convolutional neural networks (CNNs), which employ a linked parallel structure to rank similarity between inputs. Siamese networks have powerful capabilities that include effective learning with few samples and noisy inputs. This paper focuses on the advantages that siamese CNNs exhibit for classification of quite similar wireless signal emitters across signal-to-noise ratio (SNR) and dataset size. Without any a priori information, candidate siamese and baseline CNNs were trained on compressed spectrogram images to distinguish modulated signal pulses with randomized symbols and identical signal parameters, save for slight frequency offsets commonly exhibited in commercial RF emitter reference oscillator uncertainty distributions. Compared with baseline CNN approaches the proposed methods demonstrate improved classification performance under poor SNR. Moreover, this advantage holds the potential for superior, low-SNR, semi-supervised classification using embeddings from within the networks.
{"title":"Robust Signal Classification Using Siamese Networks","authors":"Zachary L. Langford, Logan Eisenbeiser, Matthew Vondal","doi":"10.1145/3324921.3328781","DOIUrl":"https://doi.org/10.1145/3324921.3328781","url":null,"abstract":"We propose a noise-robust signal classification approach using siamese convolutional neural networks (CNNs), which employ a linked parallel structure to rank similarity between inputs. Siamese networks have powerful capabilities that include effective learning with few samples and noisy inputs. This paper focuses on the advantages that siamese CNNs exhibit for classification of quite similar wireless signal emitters across signal-to-noise ratio (SNR) and dataset size. Without any a priori information, candidate siamese and baseline CNNs were trained on compressed spectrogram images to distinguish modulated signal pulses with randomized symbols and identical signal parameters, save for slight frequency offsets commonly exhibited in commercial RF emitter reference oscillator uncertainty distributions. Compared with baseline CNN approaches the proposed methods demonstrate improved classification performance under poor SNR. Moreover, this advantage holds the potential for superior, low-SNR, semi-supervised classification using embeddings from within the networks.","PeriodicalId":435733,"journal":{"name":"Proceedings of the ACM Workshop on Wireless Security and Machine Learning","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132046526","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 spread of wireless application, huge amount of data is generated every day. Thanks to its elasticity, machine learning is becoming a fundamental brick in this field, and many of applications are developed with the use of it and the several techniques that it offers. However, machine learning suffers on different problems and people that use it often are not aware of the possible threats. Often, an adversary tries to exploit these vulnerabilities in order to obtain benefits; because of this, adversarial machine learning is becoming wide studied in the scientific community. In this paper, we show state-of-the-art adversarial techniques and possible countermeasures, with the aim of warning people regarding sensible argument related to the machine learning.
{"title":"Threat is in the Air: Machine Learning for Wireless Network Applications","authors":"Luca Pajola, Luca Pasa, M. Conti","doi":"10.1145/3324921.3328783","DOIUrl":"https://doi.org/10.1145/3324921.3328783","url":null,"abstract":"With the spread of wireless application, huge amount of data is generated every day. Thanks to its elasticity, machine learning is becoming a fundamental brick in this field, and many of applications are developed with the use of it and the several techniques that it offers. However, machine learning suffers on different problems and people that use it often are not aware of the possible threats. Often, an adversary tries to exploit these vulnerabilities in order to obtain benefits; because of this, adversarial machine learning is becoming wide studied in the scientific community. In this paper, we show state-of-the-art adversarial techniques and possible countermeasures, with the aim of warning people regarding sensible argument related to the machine learning.","PeriodicalId":435733,"journal":{"name":"Proceedings of the ACM Workshop on Wireless Security and Machine Learning","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128853497","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}
We introduce a set of techniques to achieve transfer learning from computer vision to RF spectrum analysis. In this paper, we demonstrate the usefulness of this approach to scale the learning, accuracy, and efficiency of detection of adversarial and unintentional communications collisions using VGG-16. We achieve high accuracy (94% collisions detected) on a DARPA Spectrum Collaboration Challenge (SC2) dataset.
{"title":"Towards Adversarial and Unintentional Collisions Detection Using Deep Learning","authors":"H. Nguyen, T. Vo-Huu, Triet Vo Huu, G. Noubir","doi":"10.1145/3324921.3328784","DOIUrl":"https://doi.org/10.1145/3324921.3328784","url":null,"abstract":"We introduce a set of techniques to achieve transfer learning from computer vision to RF spectrum analysis. In this paper, we demonstrate the usefulness of this approach to scale the learning, accuracy, and efficiency of detection of adversarial and unintentional communications collisions using VGG-16. We achieve high accuracy (94% collisions detected) on a DARPA Spectrum Collaboration Challenge (SC2) dataset.","PeriodicalId":435733,"journal":{"name":"Proceedings of the ACM Workshop on Wireless Security and Machine Learning","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128970703","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}
Wireless communication networks are subject to various types of adversarial attacks, which might be passive in the form of eavesdropping, or active in the form of jamming. For the former category, even if the traffic is encrypted, an adversary performing analysis on observed traffic signatures may lead to leakage of the so called contextual information regarding the traffic. New advances in the field of machine learning also result in significantly more complex adversarial units, which may deduce different forms and uses of such contextual information. In this work, we are interested in power adaptation against an intelligent adversary which utilizes deep learning and attempts to perform predictions and time forecasting on the observed traffic traces to estimate the imminent traffic intensities. Based on its traffic predictions, the adversary might possibly activate its jamming mode and utilize its limited power more efficiently to inflict maximal damage. As a method of mitigation, the transmitter may want to increase transmitter power if it expects a higher probability of jamming, and it has a significant amount of upcoming data to transmit. We leverage Lyapunov optimization and virtual queues to meet a certain level of data transmission reliability while also minimizing power consumption.
{"title":"Efficient Power Adaptation against Deep Learning Based Predictive Adversaries","authors":"E. Ciftcioglu, Mike Ricos","doi":"10.1145/3324921.3328787","DOIUrl":"https://doi.org/10.1145/3324921.3328787","url":null,"abstract":"Wireless communication networks are subject to various types of adversarial attacks, which might be passive in the form of eavesdropping, or active in the form of jamming. For the former category, even if the traffic is encrypted, an adversary performing analysis on observed traffic signatures may lead to leakage of the so called contextual information regarding the traffic. New advances in the field of machine learning also result in significantly more complex adversarial units, which may deduce different forms and uses of such contextual information. In this work, we are interested in power adaptation against an intelligent adversary which utilizes deep learning and attempts to perform predictions and time forecasting on the observed traffic traces to estimate the imminent traffic intensities. Based on its traffic predictions, the adversary might possibly activate its jamming mode and utilize its limited power more efficiently to inflict maximal damage. As a method of mitigation, the transmitter may want to increase transmitter power if it expects a higher probability of jamming, and it has a significant amount of upcoming data to transmit. We leverage Lyapunov optimization and virtual queues to meet a certain level of data transmission reliability while also minimizing power consumption.","PeriodicalId":435733,"journal":{"name":"Proceedings of the ACM Workshop on Wireless Security and Machine Learning","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121117111","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}
Mobile crowdsensing (MCS) is a cloud-inspired and non-dedicated sensing paradigm to enable ubiquitous sensing via built-in sensors of personalized devices. Due to disparate participants and sensing tasks, MCS is vulnerable to threats initiated by malicious participants, which can either be a participant providing sensory data or an end user injecting a fake task aiming at resource (e.g. battery, sensor, etc.) clogging at the participating devices. This paper builds on machine learning-based detection of illegitimate tasks, and investigates the impact of machine learning-based prevention of battery-oriented illegitimate task injection in MCS campaigns. To this end, we introduce two different attack strategies, and test the impact of ML-based detection and elimination of fake tasks on task completion rate, as well as the overall battery drain of participating devices. Simulation results confirm that up to 14% battery power can be saved at the expense of a slight decrease in the completion rate of legitimate tasks.
{"title":"Machine Learning-based Prevention of Battery-oriented Illegitimate Task Injection in Mobile Crowdsensing","authors":"Yueqian Zhang, Murat Simsek, B. Kantarci","doi":"10.1145/3324921.3328786","DOIUrl":"https://doi.org/10.1145/3324921.3328786","url":null,"abstract":"Mobile crowdsensing (MCS) is a cloud-inspired and non-dedicated sensing paradigm to enable ubiquitous sensing via built-in sensors of personalized devices. Due to disparate participants and sensing tasks, MCS is vulnerable to threats initiated by malicious participants, which can either be a participant providing sensory data or an end user injecting a fake task aiming at resource (e.g. battery, sensor, etc.) clogging at the participating devices. This paper builds on machine learning-based detection of illegitimate tasks, and investigates the impact of machine learning-based prevention of battery-oriented illegitimate task injection in MCS campaigns. To this end, we introduce two different attack strategies, and test the impact of ML-based detection and elimination of fake tasks on task completion rate, as well as the overall battery drain of participating devices. Simulation results confirm that up to 14% battery power can be saved at the expense of a slight decrease in the completion rate of legitimate tasks.","PeriodicalId":435733,"journal":{"name":"Proceedings of the ACM Workshop on Wireless Security and Machine Learning","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124710852","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}
Adversarial examples (AdExs) in machine learning for classification of radio frequency (RF) signals can be created in a targeted manner such that they go beyond general misclassification and result in the detection of a specific targeted class. Moreover, these drastic, targeted misclassifications can be achieved with minimal waveform perturbations, resulting in catastrophic impact to deep learning based spectrum sensing applications (e.g. WiFi is mistaken for Bluetooth). This work addresses targeted deep learning AdExs, specifically those obtained using the Carlini-Wagner algorithm, and analyzes previously introduced defense mechanisms that performed successfully against non-targeted FGSM-based attacks. To analyze the effects of the Carlini-Wagner attack, and the defense mechanisms, we trained neural networks on two datasets. The first dataset is a subset of the DeepSig dataset, comprised of three synthetic modulations BPSK, QPSK, 8-PSK, which we use to train a simple network for Modulation Recognition. The second dataset contains real-world, well-labeled, curated data from the 2.4 GHz Industrial, Scientific and Medical (ISM) band, that we use to train a network for wireless technology (protocol) classification using three classes: WiFi 802.11n, Bluetooth (BT) and ZigBee. We show that for attacks of limited intensity the impact of the attack in terms of percentage of misclassifications is similar for both datasets, and that the proposed defense is effective in both cases. Finally, we use our ISM data to show that the targeted attack is effective against the deep learning classifier but not against a classical demodulator.
{"title":"Targeted Adversarial Examples Against RF Deep Classifiers","authors":"S. Kokalj-Filipovic, Rob Miller, Joshua Morman","doi":"10.1145/3324921.3328792","DOIUrl":"https://doi.org/10.1145/3324921.3328792","url":null,"abstract":"Adversarial examples (AdExs) in machine learning for classification of radio frequency (RF) signals can be created in a targeted manner such that they go beyond general misclassification and result in the detection of a specific targeted class. Moreover, these drastic, targeted misclassifications can be achieved with minimal waveform perturbations, resulting in catastrophic impact to deep learning based spectrum sensing applications (e.g. WiFi is mistaken for Bluetooth). This work addresses targeted deep learning AdExs, specifically those obtained using the Carlini-Wagner algorithm, and analyzes previously introduced defense mechanisms that performed successfully against non-targeted FGSM-based attacks. To analyze the effects of the Carlini-Wagner attack, and the defense mechanisms, we trained neural networks on two datasets. The first dataset is a subset of the DeepSig dataset, comprised of three synthetic modulations BPSK, QPSK, 8-PSK, which we use to train a simple network for Modulation Recognition. The second dataset contains real-world, well-labeled, curated data from the 2.4 GHz Industrial, Scientific and Medical (ISM) band, that we use to train a network for wireless technology (protocol) classification using three classes: WiFi 802.11n, Bluetooth (BT) and ZigBee. We show that for attacks of limited intensity the impact of the attack in terms of percentage of misclassifications is similar for both datasets, and that the proposed defense is effective in both cases. Finally, we use our ISM data to show that the targeted attack is effective against the deep learning classifier but not against a classical demodulator.","PeriodicalId":435733,"journal":{"name":"Proceedings of the ACM Workshop on Wireless Security and Machine Learning","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115041234","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}
Savio Sciancalepore, O. A. Ibrahim, G. Oligeri, R. D. Pietro
We propose a methodology to detect the current status of a powered-on drone (flying or at rest), leveraging just the communication traffic exchanged between the drone and its Remote Controller (RC). Our solution, other than being the first of its kind, does not require either any special hardware or to transmit any signal; it is built applying standard classification algorithms to the eavesdropped traffic, analyzing features such as packets inter-arrival time and size. Moreover, it is fully passive and it resorts to cheap and general purpose hardware. To evaluate the effectiveness of our solution, we collected real communication measurements from a drone running the widespread ArduCopter open-source firmware, mounted onboard on a wide range of commercial amateur drones. The results prove that our methodology can efficiently and effectively identify the current state of a powered-on drone, i.e., if it is flying or lying on the ground. In addition, we estimate a lower bound on the time required to identify the status of a drone with the requested level of assurance. The quality and viability of our solution do prove that network traffic analysis can be successfully adopted for drone status identification, and pave the way for future research in the area.
{"title":"Detecting Drones Status via Encrypted Traffic Analysis","authors":"Savio Sciancalepore, O. A. Ibrahim, G. Oligeri, R. D. Pietro","doi":"10.1145/3324921.3328791","DOIUrl":"https://doi.org/10.1145/3324921.3328791","url":null,"abstract":"We propose a methodology to detect the current status of a powered-on drone (flying or at rest), leveraging just the communication traffic exchanged between the drone and its Remote Controller (RC). Our solution, other than being the first of its kind, does not require either any special hardware or to transmit any signal; it is built applying standard classification algorithms to the eavesdropped traffic, analyzing features such as packets inter-arrival time and size. Moreover, it is fully passive and it resorts to cheap and general purpose hardware. To evaluate the effectiveness of our solution, we collected real communication measurements from a drone running the widespread ArduCopter open-source firmware, mounted onboard on a wide range of commercial amateur drones. The results prove that our methodology can efficiently and effectively identify the current state of a powered-on drone, i.e., if it is flying or lying on the ground. In addition, we estimate a lower bound on the time required to identify the status of a drone with the requested level of assurance. The quality and viability of our solution do prove that network traffic analysis can be successfully adopted for drone status identification, and pave the way for future research in the area.","PeriodicalId":435733,"journal":{"name":"Proceedings of the ACM Workshop on Wireless Security and Machine Learning","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123013714","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}
Wireless networks are prone to jamming attacks due to the broadcast nature of the wireless transmission environment. The effect of jamming attacks can be further increased as the jammers can focus their signals on reference signals of the transmitters, to further deteriorate the transmission performance. In this paper, we aim to jointly determine the presence of the jammer, along with its attack characteristics by using neural networks. Two neural network architectures are implemented; deep convolutional neural networks and deep recurrent neural networks. The presence of jammer and the transmitter and the type of the jammer is determined through a diverse set of scenarios that are implemented on software defined radios using orthogonal frequency division multiplexing based signaling. To improve the detection performance, prepossessing techniques are applied. Test results show that the proposed approach can effectively detect and classify the jamming attacks with around 85% accuracy.
{"title":"Jammer Detection based on Artificial Neural Networks: A Measurement Study","authors":"Selen Gecgel, Caner Goztepe, Günes Karabulut-Kurt","doi":"10.1145/3324921.3328788","DOIUrl":"https://doi.org/10.1145/3324921.3328788","url":null,"abstract":"Wireless networks are prone to jamming attacks due to the broadcast nature of the wireless transmission environment. The effect of jamming attacks can be further increased as the jammers can focus their signals on reference signals of the transmitters, to further deteriorate the transmission performance. In this paper, we aim to jointly determine the presence of the jammer, along with its attack characteristics by using neural networks. Two neural network architectures are implemented; deep convolutional neural networks and deep recurrent neural networks. The presence of jammer and the transmitter and the type of the jammer is determined through a diverse set of scenarios that are implemented on software defined radios using orthogonal frequency division multiplexing based signaling. To improve the detection performance, prepossessing techniques are applied. Test results show that the proposed approach can effectively detect and classify the jamming attacks with around 85% accuracy.","PeriodicalId":435733,"journal":{"name":"Proceedings of the ACM Workshop on Wireless Security and Machine Learning","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132404108","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：