Nowadays, IoT and smart cities are increasingly becoming popular topics among both researchers and practitioners. IoT applications are the main backbone for building a smart city.
Many governments use IoT applications to provide better services for their citizens, and other
non-governmental organizations also use them to provide better services and products for their
customers. Moreover, the day-to-day activities of society and device interactions in a smart
city are carried out over IoT applications. Conversely, new and intelligent attacks are greatly
increasing due to the behavior of these applications. As a result, security becomes one of the
most crucial concerns that need to be addressed. To date, several intrusion detection models
have been proposed by several researchers for ensuring the security of IoT devices in the smart
city. In this thesis, I proposed deep neural network-based models MLP, LSTM, and GRU for
detecting binary and muti-class IoT cyber attacks, using an imbalanced big data set. The most
recent datasets, UNSW-NB15 and CICIDS 2017, were used for model training and evaluation,
which are enhanced by a variety of recently added cyber attacks. The experimental results
for the UNSW-NB15 dataset show that the MLP model outperformed other models in terms
of recall, precision, F1-score, and FPR (false positive rate) with values of 99.17%, 99.17%,
99.17%, and 0.0037, respectively. Furthermore, the LSTM model achieved a higher accuracy
of 99.26%. In the case of conventional and ensemble models, Random Forest outclasses other
models with respect to all metrics when trained and evaluated with the UNSW-NB15 dataset.
Further, when the dataset CICIDS2017 was used for training and evaluating the Random Forest model, it outperformed other conventional and ensemble methods. Among the deep neural
network models, the MLP model classified attacks with the accuracy of 98.10%, precision of
98.20%, F1-score of 98.12%, and FPR of 0.0202, which makes it the best-performing deep
learning model.
Anotace v angličtině
Nowadays, IoT and smart cities are increasingly becoming popular topics among both researchers and practitioners. IoT applications are the main backbone for building a smart city.
Many governments use IoT applications to provide better services for their citizens, and other
non-governmental organizations also use them to provide better services and products for their
customers. Moreover, the day-to-day activities of society and device interactions in a smart
city are carried out over IoT applications. Conversely, new and intelligent attacks are greatly
increasing due to the behavior of these applications. As a result, security becomes one of the
most crucial concerns that need to be addressed. To date, several intrusion detection models
have been proposed by several researchers for ensuring the security of IoT devices in the smart
city. In this thesis, I proposed deep neural network-based models MLP, LSTM, and GRU for
detecting binary and muti-class IoT cyber attacks, using an imbalanced big data set. The most
recent datasets, UNSW-NB15 and CICIDS 2017, were used for model training and evaluation,
which are enhanced by a variety of recently added cyber attacks. The experimental results
for the UNSW-NB15 dataset show that the MLP model outperformed other models in terms
of recall, precision, F1-score, and FPR (false positive rate) with values of 99.17%, 99.17%,
99.17%, and 0.0037, respectively. Furthermore, the LSTM model achieved a higher accuracy
of 99.26%. In the case of conventional and ensemble models, Random Forest outclasses other
models with respect to all metrics when trained and evaluated with the UNSW-NB15 dataset.
Further, when the dataset CICIDS2017 was used for training and evaluating the Random Forest model, it outperformed other conventional and ensemble methods. Among the deep neural
network models, the MLP model classified attacks with the accuracy of 98.10%, precision of
98.20%, F1-score of 98.12%, and FPR of 0.0202, which makes it the best-performing deep
learning model.
Klíčová slova
IoT, Cyber Attack, Smart City, Attack Detection, Deep Learning, Big Data.
Klíčová slova v angličtině
IoT, Cyber Attack, Smart City, Attack Detection, Deep Learning, Big Data
Rozsah průvodní práce
83 pp. (129,560 characters)
Jazyk
AN
Anotace
Nowadays, IoT and smart cities are increasingly becoming popular topics among both researchers and practitioners. IoT applications are the main backbone for building a smart city.
Many governments use IoT applications to provide better services for their citizens, and other
non-governmental organizations also use them to provide better services and products for their
customers. Moreover, the day-to-day activities of society and device interactions in a smart
city are carried out over IoT applications. Conversely, new and intelligent attacks are greatly
increasing due to the behavior of these applications. As a result, security becomes one of the
most crucial concerns that need to be addressed. To date, several intrusion detection models
have been proposed by several researchers for ensuring the security of IoT devices in the smart
city. In this thesis, I proposed deep neural network-based models MLP, LSTM, and GRU for
detecting binary and muti-class IoT cyber attacks, using an imbalanced big data set. The most
recent datasets, UNSW-NB15 and CICIDS 2017, were used for model training and evaluation,
which are enhanced by a variety of recently added cyber attacks. The experimental results
for the UNSW-NB15 dataset show that the MLP model outperformed other models in terms
of recall, precision, F1-score, and FPR (false positive rate) with values of 99.17%, 99.17%,
99.17%, and 0.0037, respectively. Furthermore, the LSTM model achieved a higher accuracy
of 99.26%. In the case of conventional and ensemble models, Random Forest outclasses other
models with respect to all metrics when trained and evaluated with the UNSW-NB15 dataset.
Further, when the dataset CICIDS2017 was used for training and evaluating the Random Forest model, it outperformed other conventional and ensemble methods. Among the deep neural
network models, the MLP model classified attacks with the accuracy of 98.10%, precision of
98.20%, F1-score of 98.12%, and FPR of 0.0202, which makes it the best-performing deep
learning model.
Anotace v angličtině
Nowadays, IoT and smart cities are increasingly becoming popular topics among both researchers and practitioners. IoT applications are the main backbone for building a smart city.
Many governments use IoT applications to provide better services for their citizens, and other
non-governmental organizations also use them to provide better services and products for their
customers. Moreover, the day-to-day activities of society and device interactions in a smart
city are carried out over IoT applications. Conversely, new and intelligent attacks are greatly
increasing due to the behavior of these applications. As a result, security becomes one of the
most crucial concerns that need to be addressed. To date, several intrusion detection models
have been proposed by several researchers for ensuring the security of IoT devices in the smart
city. In this thesis, I proposed deep neural network-based models MLP, LSTM, and GRU for
detecting binary and muti-class IoT cyber attacks, using an imbalanced big data set. The most
recent datasets, UNSW-NB15 and CICIDS 2017, were used for model training and evaluation,
which are enhanced by a variety of recently added cyber attacks. The experimental results
for the UNSW-NB15 dataset show that the MLP model outperformed other models in terms
of recall, precision, F1-score, and FPR (false positive rate) with values of 99.17%, 99.17%,
99.17%, and 0.0037, respectively. Furthermore, the LSTM model achieved a higher accuracy
of 99.26%. In the case of conventional and ensemble models, Random Forest outclasses other
models with respect to all metrics when trained and evaluated with the UNSW-NB15 dataset.
Further, when the dataset CICIDS2017 was used for training and evaluating the Random Forest model, it outperformed other conventional and ensemble methods. Among the deep neural
network models, the MLP model classified attacks with the accuracy of 98.10%, precision of
98.20%, F1-score of 98.12%, and FPR of 0.0202, which makes it the best-performing deep
learning model.
Klíčová slova
IoT, Cyber Attack, Smart City, Attack Detection, Deep Learning, Big Data.
Klíčová slova v angličtině
IoT, Cyber Attack, Smart City, Attack Detection, Deep Learning, Big Data
Zásady pro vypracování
Objective: Characterize IoT architecture for smart cities, summarize existing approaches to detecting IoT cyberattacks, propose a deep neural network-based model for detecting IoT cyberattacks, validate the model using datasets relevant for smart cities, and discuss implications of the results for smart cities.
Outline
-- IoT cyberattacks in smart cities.
-- Machine learning and deep neural networks.
-- Data collection for smart city IoT cyberattack detection.
-- Model for detection of IoT cyberattacks in smart cities.
-- Evaluation and discussion of results.
Zásady pro vypracování
Objective: Characterize IoT architecture for smart cities, summarize existing approaches to detecting IoT cyberattacks, propose a deep neural network-based model for detecting IoT cyberattacks, validate the model using datasets relevant for smart cities, and discuss implications of the results for smart cities.
Outline
-- IoT cyberattacks in smart cities.
-- Machine learning and deep neural networks.
-- Data collection for smart city IoT cyberattack detection.
-- Model for detection of IoT cyberattacks in smart cities.
-- Evaluation and discussion of results.
Seznam doporučené literatury
AL-TALEB, N., SAQIB, N. A. Towards a hybrid machine learning model for intelligent cyber threat identification in smart city environments. Applied Sciences,, 2022, 12, p. 1863.
CHEN, D., WAWRZYNSKI, P., Zhihan, L. V. Cyber security in smart cities: A review of deep learning-based applications and case studies. Sustainable Cities and Society, 2021, 66, p. 102655.
MEIDAN, Y., BOHADANA, M., MATHOV, Y., MIRSKY, Y., SHABTAI, A., BREITENBACHER, D., ELOVICI, Y. N-BaIoT: Network-based detection of IoT botnet attacks using deep autoencoders. IEEE Pervasive Computing, 2018, 17, p. 12-22.
SHAFIQ, M., TIAN, Z., SUN, Y., DU, X., GUIZANI, M. Selection of effective machine learning algorithm and Bot-IoT attacks traffic identification for internet of things in smart city. Future Generation Computer Systems, 2020, 107, p. 433-442.
VINAYAKUMAR, R., ALAZAB, M., SOMAN, K. P., POORNACHANDRAN, P., AL-NEMRAT, A., VENKATRAMAN, S. Deep learning approach for intelligent intrusion detection system. Ieee Access, 2019, 7, p. 41525-41550.
Seznam doporučené literatury
AL-TALEB, N., SAQIB, N. A. Towards a hybrid machine learning model for intelligent cyber threat identification in smart city environments. Applied Sciences,, 2022, 12, p. 1863.
CHEN, D., WAWRZYNSKI, P., Zhihan, L. V. Cyber security in smart cities: A review of deep learning-based applications and case studies. Sustainable Cities and Society, 2021, 66, p. 102655.
MEIDAN, Y., BOHADANA, M., MATHOV, Y., MIRSKY, Y., SHABTAI, A., BREITENBACHER, D., ELOVICI, Y. N-BaIoT: Network-based detection of IoT botnet attacks using deep autoencoders. IEEE Pervasive Computing, 2018, 17, p. 12-22.
SHAFIQ, M., TIAN, Z., SUN, Y., DU, X., GUIZANI, M. Selection of effective machine learning algorithm and Bot-IoT attacks traffic identification for internet of things in smart city. Future Generation Computer Systems, 2020, 107, p. 433-442.
VINAYAKUMAR, R., ALAZAB, M., SOMAN, K. P., POORNACHANDRAN, P., AL-NEMRAT, A., VENKATRAMAN, S. Deep learning approach for intelligent intrusion detection system. Ieee Access, 2019, 7, p. 41525-41550.
Přílohy volně vložené
-
Přílohy vázané v práci
ilustrace, grafy, schémata, portréty, tabulky
Převzato z knihovny
Ne
Plný text práce
Přílohy
Posudek(y) oponenta
Hodnocení vedoucího
Záznam průběhu obhajoby
The student defended master ‘s thesis named: Detection of IoT Cyberattacks in Smart Cities using Deep Neural Networks. Aim of thesis is to summarize existing approaches to detecting IoT cyber-attacks, propose a DNN-based model for detecting IoT cyber-attacks, validate the model using datasets relevant to smart cities, and discuss implications of the results for smart cities.
Questions and suggestions for defense by supervisor and reviewer
Deep learning models detect most cyber-attacks with high accuracy. However, some attacks have proven to be resistant to detection. Try to explain these results.
What are the implications of further IoT expansion for cyber-attack detection?
The quantitative indicators on page 42 indicate that you give equal weight to False Positive (FP) and False Negative (FN) errors, while the consequences of these errors are very different. How do you deal with this fact?
Based on your work, can you formulate any security measures that will reduce the risk of some IoT attacks being successful?
The student responded to the commission's questions.