{"title":"Proceedings of the 2nd ACM Workshop on Wireless Security and Machine Learning","authors":"Michael Roland","doi":"10.1145/3395352","DOIUrl":"https://doi.org/10.1145/3395352","url":null,"abstract":"","PeriodicalId":370816,"journal":{"name":"Proceedings of the 2nd ACM Workshop on Wireless Security and Machine Learning","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128233390","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
S. Kokalj-Filipovic, Morriel Kasher, Michael Zhao, P. Spasojevic
The novel secret inaudible acoustic communication channel [11], referred to as the BackDoor channel, is a method of embedding inaudible signals in acoustic data that is likely to be processed by a trained deep neural net. In this paper we perform preliminary studies of the detectability of such a communication channel by deep learning algorithms that are trained on the original acoustic data used for such a secret exploit. The BackDoor channel embeds inaudible messages by modulating them with a sinewave of 40kHz and transmitting using ultrasonic speakers. The received composite signal is used to generate the Backdoor dataset for evaluation of our neural net. The audible samples are played back and recorded as a baseline dataset for training. The Backdoor dataset is used to evaluate the impact that the BackDoor channel has on the classification of the acoustic data, and we show that the accuracy of the classifier is degraded. The degradation depends on the type of deep classifier and it appears to impact less the classifiers that are trained using autoencoders. We also propose statistics that can be used to detect the out-of-distribution samples created as a result of the BackDoor channel, such as the log likelihood of the variational autoencoder used to pre-train the classifier or the empirical entropy of the classifier's output layer. The preliminary results presented in this paper indicate that the use of deep learning classifiers as detectors of the BackDoor secret channel merits further research.
{"title":"Detecting acoustic backdoor transmission of inaudible messages using deep learning","authors":"S. Kokalj-Filipovic, Morriel Kasher, Michael Zhao, P. Spasojevic","doi":"10.1145/3395352.3402629","DOIUrl":"https://doi.org/10.1145/3395352.3402629","url":null,"abstract":"The novel secret inaudible acoustic communication channel [11], referred to as the BackDoor channel, is a method of embedding inaudible signals in acoustic data that is likely to be processed by a trained deep neural net. In this paper we perform preliminary studies of the detectability of such a communication channel by deep learning algorithms that are trained on the original acoustic data used for such a secret exploit. The BackDoor channel embeds inaudible messages by modulating them with a sinewave of 40kHz and transmitting using ultrasonic speakers. The received composite signal is used to generate the Backdoor dataset for evaluation of our neural net. The audible samples are played back and recorded as a baseline dataset for training. The Backdoor dataset is used to evaluate the impact that the BackDoor channel has on the classification of the acoustic data, and we show that the accuracy of the classifier is degraded. The degradation depends on the type of deep classifier and it appears to impact less the classifiers that are trained using autoencoders. We also propose statistics that can be used to detect the out-of-distribution samples created as a result of the BackDoor channel, such as the log likelihood of the variational autoencoder used to pre-train the classifier or the empirical entropy of the classifier's output layer. The preliminary results presented in this paper indicate that the use of deep learning classifiers as detectors of the BackDoor secret channel merits further research.","PeriodicalId":370816,"journal":{"name":"Proceedings of the 2nd ACM Workshop on Wireless Security and Machine Learning","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129003867","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}
The discovery of practical adversarial machine learning (AML) attacks against machine learning-based wired and wireless network security detectors has driven the necessity of a defense. Without a defense mechanism against AML, attacks in wired and wireless networks will go unnoticed by network security classifiers resulting in their ineffectiveness. Therefore, it is essential to motivate a defense against AML attacks for network security classifiers. Existing AML defenses are generally within the context of image recognition. However, these AML defenses have limited transferability to a network security context. Unlike image recognition, a subject matter expert generally derives the features of a network security classifier. Therefore, a network security classifier requires a distinctive strategy for defense. We propose a novel defense-in-depth approach for network security classifiers using a hierarchical ensemble of classifiers, each using a disparate feature set. Subsequently we show the effective use of our hierarchical ensemble to defend an existing network security classifier against an AML attack. Additionally, we discover a novel set of features to detect network scanning activity. Lastly, we propose to enhance our AML defense approach in future work. A shortcoming of our approach is the increased cost to the defender for implementation of each independent classifier. Therefore, we propose combining our AML defense with a moving target defense approach. Additionally, we propose to evaluate our AML defense with a variety of datasets and classifiers and evaluate the effectiveness of decomposing a classifier with many features into multiple classifiers, each with a small subset of the features.
{"title":"A network security classifier defense: against adversarial machine learning attacks","authors":"Michael J. De Lucia, Chase Cotton","doi":"10.1145/3395352.3402627","DOIUrl":"https://doi.org/10.1145/3395352.3402627","url":null,"abstract":"The discovery of practical adversarial machine learning (AML) attacks against machine learning-based wired and wireless network security detectors has driven the necessity of a defense. Without a defense mechanism against AML, attacks in wired and wireless networks will go unnoticed by network security classifiers resulting in their ineffectiveness. Therefore, it is essential to motivate a defense against AML attacks for network security classifiers. Existing AML defenses are generally within the context of image recognition. However, these AML defenses have limited transferability to a network security context. Unlike image recognition, a subject matter expert generally derives the features of a network security classifier. Therefore, a network security classifier requires a distinctive strategy for defense. We propose a novel defense-in-depth approach for network security classifiers using a hierarchical ensemble of classifiers, each using a disparate feature set. Subsequently we show the effective use of our hierarchical ensemble to defend an existing network security classifier against an AML attack. Additionally, we discover a novel set of features to detect network scanning activity. Lastly, we propose to enhance our AML defense approach in future work. A shortcoming of our approach is the increased cost to the defender for implementation of each independent classifier. Therefore, we propose combining our AML defense with a moving target defense approach. Additionally, we propose to evaluate our AML defense with a variety of datasets and classifiers and evaluate the effectiveness of decomposing a classifier with many features into multiple classifiers, each with a small subset of the features.","PeriodicalId":370816,"journal":{"name":"Proceedings of the 2nd ACM Workshop on Wireless Security and Machine Learning","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130079140","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}
Deep learning has great potential for automatic modulation classification (AMC). However, its performance largely hinges upon the availability of sufficient high-quality labeled data. In this paper, we propose data augmentation with conditional generative adversarial network (CGAN) for convolutional neural network (CNN) based AMC, which provides an effective solution to the limited data problem. We present the design of the proposed CGAN based data augmentation method, and validate its performance with a public dataset. The experiment results show that CNN-based modulation classification can greatly benefit from the proposed data augmentation approach with greatly improved accuracy.
{"title":"Data augmentation with conditional GAN for automatic modulation classification","authors":"M. Patel, Xuyu Wang, S. Mao","doi":"10.1145/3395352.3402622","DOIUrl":"https://doi.org/10.1145/3395352.3402622","url":null,"abstract":"Deep learning has great potential for automatic modulation classification (AMC). However, its performance largely hinges upon the availability of sufficient high-quality labeled data. In this paper, we propose data augmentation with conditional generative adversarial network (CGAN) for convolutional neural network (CNN) based AMC, which provides an effective solution to the limited data problem. We present the design of the proposed CGAN based data augmentation method, and validate its performance with a public dataset. The experiment results show that CNN-based modulation classification can greatly benefit from the proposed data augmentation approach with greatly improved accuracy.","PeriodicalId":370816,"journal":{"name":"Proceedings of the 2nd ACM Workshop on Wireless Security and Machine Learning","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131010806","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}
Recently, deep learning of encoding and decoding functions for wireless communication has emerged as a promising research direction and gained considerable interest due to its impressive results. A specific direction in this growing field are neural network-aided techniques that work without a fixed channel model. These approaches utilize generative adversarial networks, reinforcement learning, or mutual information estimation to overcome the need of a known channel model for training. This paper focuses on the last approach and extend it to secure channel coding schemes by sampling the legitimate channel and additionally introduce security constraints for communication. This results in a mixed optimization between the mutual information estimate, the reliability of the code and its secrecy constraint. It is believed that this lays the foundation for flexible, generalizable physical layer security approaches due to its independence of specific model assumptions.
{"title":"Deep learning based wiretap coding via mutual information estimation","authors":"Rick Fritschek, R. Schaefer, G. Wunder","doi":"10.1145/3395352.3402654","DOIUrl":"https://doi.org/10.1145/3395352.3402654","url":null,"abstract":"Recently, deep learning of encoding and decoding functions for wireless communication has emerged as a promising research direction and gained considerable interest due to its impressive results. A specific direction in this growing field are neural network-aided techniques that work without a fixed channel model. These approaches utilize generative adversarial networks, reinforcement learning, or mutual information estimation to overcome the need of a known channel model for training. This paper focuses on the last approach and extend it to secure channel coding schemes by sampling the legitimate channel and additionally introduce security constraints for communication. This results in a mixed optimization between the mutual information estimate, the reliability of the code and its secrecy constraint. It is believed that this lays the foundation for flexible, generalizable physical layer security approaches due to its independence of specific model assumptions.","PeriodicalId":370816,"journal":{"name":"Proceedings of the 2nd ACM Workshop on Wireless Security and Machine Learning","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133901908","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}
H. Franco, Chris Cobo-Kroenke, Stephanie Welch, M. Graciarena
We present a system to perform spectral monitoring of a wide band of 666.5 MHz, located within a range of 6 GHz of Radio Frequency (RF) bandwidth, using state-of-the-art deep learning approaches. The system detects, labels, and localizes in time and frequency signals of interest (SOIs) against a background of wideband RF activity. We apply a hierarchical approach. At the lower level we use a sweeping window to analyze a wideband spectrogram, which is input to a deep convolutional network that estimates local probabilities for the presence of SOIs for each position of the window. In a subsequent, higher-level processing step, these local frame probability estimates are integrated over larger two-dimensional regions that are hypothesized by a second neural network, a region proposal network, adapted from object localization in image processing. The integrated segmental probability scores are used to detect SOIs in the hypothesized spectro-temporal regions.
{"title":"Wideband spectral monitoring using deep learning","authors":"H. Franco, Chris Cobo-Kroenke, Stephanie Welch, M. Graciarena","doi":"10.1145/3395352.3402620","DOIUrl":"https://doi.org/10.1145/3395352.3402620","url":null,"abstract":"We present a system to perform spectral monitoring of a wide band of 666.5 MHz, located within a range of 6 GHz of Radio Frequency (RF) bandwidth, using state-of-the-art deep learning approaches. The system detects, labels, and localizes in time and frequency signals of interest (SOIs) against a background of wideband RF activity. We apply a hierarchical approach. At the lower level we use a sweeping window to analyze a wideband spectrogram, which is input to a deep convolutional network that estimates local probabilities for the presence of SOIs for each position of the window. In a subsequent, higher-level processing step, these local frame probability estimates are integrated over larger two-dimensional regions that are hypothesized by a second neural network, a region proposal network, adapted from object localization in image processing. The integrated segmental probability scores are used to detect SOIs in the hypothesized spectro-temporal regions.","PeriodicalId":370816,"journal":{"name":"Proceedings of the 2nd ACM Workshop on Wireless Security and Machine Learning","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114527312","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}
Francesco Restuccia, Salvatore D’oro, Amani Al-Shawabka, Bruno Costa Rendon, K. Chowdhury, Stratis Ioannidis, T. Melodia
Deep learning techniques can classify spectrum phenomena (e.g., waveform modulation) with accuracy levels that were once thought impossible. Although we have recently seen many advances in this field, extensive work in computer vision has demonstrated that an adversary can "crack" a classifier by designing inputs that "steer" the classifier away from the ground truth. This paper advances the state of the art by proposing a generalized analysis and evaluation of adversarial machine learning (AML) attacks to deep learning systems in the wireless domain. We postulate a series of adversarial attacks, and formulate a Generalized Wireless Adversarial Machine Learning Problem (GWAP) where we analyze the combined effect of the wireless channel and the adversarial waveform on the efficacy of the attacks. We extensively evaluate the performance of our attacks on a state-of-the-art 1,000-device radio fingerprinting dataset, and a 24-class modulation dataset. Results show that our algorithms can decrease the classifiers' accuracy up to 3x while keeping the waveform distortion to a minimum.
{"title":"Generalized wireless adversarial deep learning","authors":"Francesco Restuccia, Salvatore D’oro, Amani Al-Shawabka, Bruno Costa Rendon, K. Chowdhury, Stratis Ioannidis, T. Melodia","doi":"10.1145/3395352.3402625","DOIUrl":"https://doi.org/10.1145/3395352.3402625","url":null,"abstract":"Deep learning techniques can classify spectrum phenomena (e.g., waveform modulation) with accuracy levels that were once thought impossible. Although we have recently seen many advances in this field, extensive work in computer vision has demonstrated that an adversary can \"crack\" a classifier by designing inputs that \"steer\" the classifier away from the ground truth. This paper advances the state of the art by proposing a generalized analysis and evaluation of adversarial machine learning (AML) attacks to deep learning systems in the wireless domain. We postulate a series of adversarial attacks, and formulate a Generalized Wireless Adversarial Machine Learning Problem (GWAP) where we analyze the combined effect of the wireless channel and the adversarial waveform on the efficacy of the attacks. We extensively evaluate the performance of our attacks on a state-of-the-art 1,000-device radio fingerprinting dataset, and a 24-class modulation dataset. Results show that our algorithms can decrease the classifiers' accuracy up to 3x while keeping the waveform distortion to a minimum.","PeriodicalId":370816,"journal":{"name":"Proceedings of the 2nd ACM Workshop on Wireless Security and Machine Learning","volume":"29 11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116800520","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}
Dule Shu, Weilin Cong, Jiaming Chai, Conrad S. Tucker
Steganography has received a great deal of attention within the information security domain due to its potential utility in ensuring network security and privacy. Leveraging advancements in deep neural networks, the state-of-the-art steganography models are capable of encoding a message within a cover image and producing a visually indistinguishable encoded image from which the decoder can recover the original message. While a message of different data types can be converted to a binary message before encoding into a cover image, this work explores the ability of neural network models to encode data types of different modalities. We propose the ERS-GAN (Encrypted Rich-data Steganography Generative Adversarial Network) - an end-to-end generative adversarial network model for efficient data encoding and decoding. Our proposed model is capable of encoding message of multiple types, e.g., text, audio and image, and is able to hide message deeply into a cover image without being detected and decoded by a third-party adversary who is not given permission to access the message. Experiments conducted on the datasets MS-COCO and Speech Commands show that our model out-performs or equally matches the state-of-the-arts in several aspects of steganography performance. Our proposed ERS-GAN can be potentially used to protect the wireless communication against malicious activity such as eavesdropping.
{"title":"Encrypted rich-data steganography using generative adversarial networks","authors":"Dule Shu, Weilin Cong, Jiaming Chai, Conrad S. Tucker","doi":"10.1145/3395352.3402626","DOIUrl":"https://doi.org/10.1145/3395352.3402626","url":null,"abstract":"Steganography has received a great deal of attention within the information security domain due to its potential utility in ensuring network security and privacy. Leveraging advancements in deep neural networks, the state-of-the-art steganography models are capable of encoding a message within a cover image and producing a visually indistinguishable encoded image from which the decoder can recover the original message. While a message of different data types can be converted to a binary message before encoding into a cover image, this work explores the ability of neural network models to encode data types of different modalities. We propose the ERS-GAN (Encrypted Rich-data Steganography Generative Adversarial Network) - an end-to-end generative adversarial network model for efficient data encoding and decoding. Our proposed model is capable of encoding message of multiple types, e.g., text, audio and image, and is able to hide message deeply into a cover image without being detected and decoded by a third-party adversary who is not given permission to access the message. Experiments conducted on the datasets MS-COCO and Speech Commands show that our model out-performs or equally matches the state-of-the-arts in several aspects of steganography performance. Our proposed ERS-GAN can be potentially used to protect the wireless communication against malicious activity such as eavesdropping.","PeriodicalId":370816,"journal":{"name":"Proceedings of the 2nd ACM Workshop on Wireless Security and Machine Learning","volume":"140 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123423283","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}
Dule Shu, Nandi O. Leslie, C. Kamhoua, Conrad S. Tucker
Intrusion Detection Systems (IDS) are increasingly adopting machine learning (ML)-based approaches to detect threats in computer networks due to their ability to learn underlying threat patterns/features. However, ML-based models are susceptible to adversarial attacks, attacks wherein slight perturbations of the input features, cause misclassifications. We propose a method that uses active learning and generative adversarial networks to evaluate the threat of adversarial attacks on ML-based IDS. Existing adversarial attack methods require a large amount of training data or assume knowledge of the IDS model itself (e.g., loss function), which may not be possible in real-world settings. Our method overcomes these limitations by demonstrating the ability to compromise an IDS using limited training data and assuming no prior knowledge of the IDS model other than its binary classification (i.e., benign or malicious). Experimental results demonstrate the ability of our proposed model to achieve a 98.86% success rate in bypassing the IDS model using only 25 labeled data points during model training. The knowledge gained by compromising the ML-based IDS, can be integrated into the IDS in order to enhance its robustness against similar ML-based adversarial attacks.
{"title":"Generative adversarial attacks against intrusion detection systems using active learning","authors":"Dule Shu, Nandi O. Leslie, C. Kamhoua, Conrad S. Tucker","doi":"10.1145/3395352.3402618","DOIUrl":"https://doi.org/10.1145/3395352.3402618","url":null,"abstract":"Intrusion Detection Systems (IDS) are increasingly adopting machine learning (ML)-based approaches to detect threats in computer networks due to their ability to learn underlying threat patterns/features. However, ML-based models are susceptible to adversarial attacks, attacks wherein slight perturbations of the input features, cause misclassifications. We propose a method that uses active learning and generative adversarial networks to evaluate the threat of adversarial attacks on ML-based IDS. Existing adversarial attack methods require a large amount of training data or assume knowledge of the IDS model itself (e.g., loss function), which may not be possible in real-world settings. Our method overcomes these limitations by demonstrating the ability to compromise an IDS using limited training data and assuming no prior knowledge of the IDS model other than its binary classification (i.e., benign or malicious). Experimental results demonstrate the ability of our proposed model to achieve a 98.86% success rate in bypassing the IDS model using only 25 labeled data points during model training. The knowledge gained by compromising the ML-based IDS, can be integrated into the IDS in order to enhance its robustness against similar ML-based adversarial attacks.","PeriodicalId":370816,"journal":{"name":"Proceedings of the 2nd ACM Workshop on Wireless Security and Machine Learning","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123663982","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}
Wide adoption of Internet of Things (IoT) devices and applications encounters security vulnerabilities as roadblocks. The heterogeneous nature of IoT systems prevents common benchmarks, such as the NSL-KDD dataset, from being used to test and verify the performance of different Network Intrusion Detection Systems (NIDS). In order to bridge this gap, in this paper, we examine specific attacks in the NSL-KDD dataset that can impact sensor nodes and networks in IoT settings. Furthermore, in order to detect the introduced attacks, we study eleven machine learning algorithms and report the results. Through numerical analysis, we show that tree-based methods and ensemble methods outperform the rest of the studied machine learning methods. Among the supervised algorithms, XGBoost ranks the first with 97% accuracy, 90.5% Matthews correlation coefficient (MCC), and 99.6% Area Under the Curve (AUC) performance. Moreover, a notable research finding of this study is that the Expectation-Maximization (EM) algorithm, which is an unsupervised method, also performs reasonably well in the detection of the attacks in the NSL-KDD dataset and outperforms the accuracy of the Naïve Bayes classifier by 22.0%.
{"title":"Machine learning-driven intrusion detection for Contiki-NG-based IoT networks exposed to NSL-KDD dataset","authors":"Jinxin Liu, B. Kantarci, C. Adams","doi":"10.1145/3395352.3402621","DOIUrl":"https://doi.org/10.1145/3395352.3402621","url":null,"abstract":"Wide adoption of Internet of Things (IoT) devices and applications encounters security vulnerabilities as roadblocks. The heterogeneous nature of IoT systems prevents common benchmarks, such as the NSL-KDD dataset, from being used to test and verify the performance of different Network Intrusion Detection Systems (NIDS). In order to bridge this gap, in this paper, we examine specific attacks in the NSL-KDD dataset that can impact sensor nodes and networks in IoT settings. Furthermore, in order to detect the introduced attacks, we study eleven machine learning algorithms and report the results. Through numerical analysis, we show that tree-based methods and ensemble methods outperform the rest of the studied machine learning methods. Among the supervised algorithms, XGBoost ranks the first with 97% accuracy, 90.5% Matthews correlation coefficient (MCC), and 99.6% Area Under the Curve (AUC) performance. Moreover, a notable research finding of this study is that the Expectation-Maximization (EM) algorithm, which is an unsupervised method, also performs reasonably well in the detection of the attacks in the NSL-KDD dataset and outperforms the accuracy of the Naïve Bayes classifier by 22.0%.","PeriodicalId":370816,"journal":{"name":"Proceedings of the 2nd ACM Workshop on Wireless Security and Machine Learning","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126903002","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：