Öz
Today, connected systems are widely used with the recent developments in technology. The internet-connected devices create data traffic when communicating with each other. These data may contain extremely confidential information. Observers can obtain confidential information from the traffic when the security of this traffic cannot be adequately ensured. This confidential information can be personal information as well as information about the type of device used by the person. Attackers could use machine learning to analyze encrypted data traffic patterns from IoT devices to infer sensitive information, even without decrypting the actual content. For example, if someone uses IoT devices for health monitoring or smoke detection, attackers could leverage machine learning to discern victims' habits or identify health conditions. An increase in the number of IoT devices may decrease the accuracy of classification when using machine learning. This paper presents the importance of the effect of device type number on the classification of IoT devices. Therefore, inference attacks on privacy with machine learning algorithms, attacks on machine learning models, and the padding method that is commonly used against such attacks are presented. Moreover, experiments are carried out by using the dataset of the traffic generated by the Internet of Things (IoT) devices. For this purpose, Random Forest, Decision Tree, and k-Nearest Neighbors (k-NN) classification algorithms are compared, and the accuracy rate changes according to the number of devices are presented. According to the results, the Random Forest and Decision Tree algorithms are found to be more effective than the k-NN algorithm. When considering a scenario with two device types, the Random Forest and Decision Tree algorithms achieved an accuracy rate of 98%, outperforming the k-NN algorithm, which had an accuracy rate of 95%.
Anahtar Kelimeler
Classification Internet of things (IoT) Machine learning Padding Privacy Trade-off
Proje Numarası
FM-HZP-2023-29550
Kaynakça
- Abdulkareem NM, Abdulazeez AM. 2021. Machine learning classification based on Random Forest Algorithm: A review. IJSB, 5(2): 128-142.
- Aksoy A, Gunes MH. 2019. Automated IoT device identification using network traffic. In: ICC 2019 - IEEE International Conference on Communications, 20-24 May, Shanghai, China, pp: 1-7.
- Alex C, Creado G, Almobaideen W, Alghanam OA, Saadeh M. 2023. A Comprehensive survey for IoT security datasets taxonomy classification and machine learning mechanisms. COSE, 134: 103283.
- Alghuried A. 2017. A model for anomalies detection in internet of things (IoT): using inverse weight clustering and decision tree. MSc thesis, Dublin Institute of Technology, Dublin, Ireland, pp: 142.
- Biggio B, Nelson B, Laskov P. 2012. poisoning attacks against support vector machines. arXiv, 1206.6389.
- Biggio B, Corona I, Maiorca D, Nelson B, Šrndić N, Laskov P, Roli F. 2013. Evasion attacks against machine learning at test time. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, 23-27 September 2013, Prague, Czech Republic, pp: 387-402.
- Charbuty B, Abdulazeez A. 2021. Classification based on decision tree algorithm for machine learning. JASTT, 2(01): 20-28.
- Dogru N, Subasi A. 2018. Traffic accident detection using random forest classifier. In: 15th Learning and Technology Conference (L&T), 25-27 February 2018, Jeddah, Saudi Arabia, pp: 40-45.
- Ergün A, Can Ö. 2022a. Machine learning attacks against internet of things devices. IJMSIT, 6(1): 23-28.
- Ergün A, Can Ö. 2022b. Ensuring IoT Privacy using padding strategies against machine learning approaches. IJMSIT, 6(2): 193-197.
- Gawri B, Kasturi A, Neti LBM, Hota C. 2022. An efficient approach to kNN algorithm for IoT Devices. In: 2022 14th International Conference on Communication Systems & Networks (COMSNETS), 3-8 January 2022, Bengaluru, India, pp: 734-738.
- Kröger J. 2018. Unexpected inferences from sensor data: a hidden privacy threat in the internet of things. In: IFIP International Internet of Things Conference, 5-8 November 2018, Valencia, Spain, pp: 147-159.
- Kwon H, Kim Y, Park KW, Yoon H, Choi D. 2018. Multi-targeted adversarial example in evasion attack on deep neural network. IEEE Access, 6: 46084-46096.
- Pinheiro AJ, de Araujo-Filho PF, Bezerra JDM, Campelo DR. 2020. Adaptive packet padding approach for smart home networks: a tradeoff between privacy and performance. IEEE IoT-J, 8(5): 3930-3938.
- Sivanathan A, Gharakheili HH, Loi F, Radford A, Wijenayake C, Vishwanath A, Sivaraman V. 2018. Classifying IoT devices in smart environments using network traffic characteristics. IEEE TMC, 18(8): 1745-1759.
- Tolpegin V, Truex S, Gursoy ME, Liu L. 2020. Data poisoning attacks against federated learning systems. In: European Symposium on Research in Computer Security, 14-18 September 2020, Guildford, United Kingdom, pp: 480-501.
- Wang H, Xu P, Zhao J. 2021. Improved KNN algorithm based on preprocessing of center in smart cities. Complexity, 2021: 1-9.
- Yerlikaya FA, Bahtiyar Ş. 2022. Data poisoning attacks against machine learning algorithms. Expert Syst Appl, 208: 118101.
Öz
Today, connected systems are widely used with the recent developments in technology. The internet-connected devices create data traffic when communicating with each other. These data may contain extremely confidential information. Observers can obtain confidential information from the traffic when the security of this traffic cannot be adequately ensured. This confidential information can be personal information as well as information about the type of device used by the person. Attackers could use machine learning to analyze encrypted data traffic patterns from IoT devices to infer sensitive information, even without decrypting the actual content. For example, if someone uses IoT devices for health monitoring or smoke detection, attackers could leverage machine learning to discern victims' habits or identify health conditions. An increase in the number of IoT devices may decrease the accuracy of classification when using machine learning. This paper presents the importance of the effect of device type number on the classification of IoT devices. Therefore, inference attacks on privacy with machine learning algorithms, attacks on machine learning models, and the padding method that is commonly used against such attacks are presented. Moreover, experiments are carried out by using the dataset of the traffic generated by the Internet of Things (IoT) devices. For this purpose, Random Forest, Decision Tree, and k-Nearest Neighbors (k-NN) classification algorithms are compared, and the accuracy rate changes according to the number of devices are presented. According to the results, the Random Forest and Decision Tree algorithms are found to be more effective than the k-NN algorithm. When considering a scenario with two device types, the Random Forest and Decision Tree algorithms achieved an accuracy rate of 98%, outperforming the k-NN algorithm, which had an accuracy rate of 95%.
Anahtar Kelimeler
Classification Internet of things (IoT) Machine learning Padding Privacy Trade-off
Destekleyen Kurum
Ege University Scientific Research Projects Committee
Proje Numarası
FM-HZP-2023-29550
Kaynakça
- Abdulkareem NM, Abdulazeez AM. 2021. Machine learning classification based on Random Forest Algorithm: A review. IJSB, 5(2): 128-142.
- Aksoy A, Gunes MH. 2019. Automated IoT device identification using network traffic. In: ICC 2019 - IEEE International Conference on Communications, 20-24 May, Shanghai, China, pp: 1-7.
- Alex C, Creado G, Almobaideen W, Alghanam OA, Saadeh M. 2023. A Comprehensive survey for IoT security datasets taxonomy classification and machine learning mechanisms. COSE, 134: 103283.
- Alghuried A. 2017. A model for anomalies detection in internet of things (IoT): using inverse weight clustering and decision tree. MSc thesis, Dublin Institute of Technology, Dublin, Ireland, pp: 142.
- Biggio B, Nelson B, Laskov P. 2012. poisoning attacks against support vector machines. arXiv, 1206.6389.
- Biggio B, Corona I, Maiorca D, Nelson B, Šrndić N, Laskov P, Roli F. 2013. Evasion attacks against machine learning at test time. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, 23-27 September 2013, Prague, Czech Republic, pp: 387-402.
- Charbuty B, Abdulazeez A. 2021. Classification based on decision tree algorithm for machine learning. JASTT, 2(01): 20-28.
- Dogru N, Subasi A. 2018. Traffic accident detection using random forest classifier. In: 15th Learning and Technology Conference (L&T), 25-27 February 2018, Jeddah, Saudi Arabia, pp: 40-45.
- Ergün A, Can Ö. 2022a. Machine learning attacks against internet of things devices. IJMSIT, 6(1): 23-28.
- Ergün A, Can Ö. 2022b. Ensuring IoT Privacy using padding strategies against machine learning approaches. IJMSIT, 6(2): 193-197.
- Gawri B, Kasturi A, Neti LBM, Hota C. 2022. An efficient approach to kNN algorithm for IoT Devices. In: 2022 14th International Conference on Communication Systems & Networks (COMSNETS), 3-8 January 2022, Bengaluru, India, pp: 734-738.
- Kröger J. 2018. Unexpected inferences from sensor data: a hidden privacy threat in the internet of things. In: IFIP International Internet of Things Conference, 5-8 November 2018, Valencia, Spain, pp: 147-159.
- Kwon H, Kim Y, Park KW, Yoon H, Choi D. 2018. Multi-targeted adversarial example in evasion attack on deep neural network. IEEE Access, 6: 46084-46096.
- Pinheiro AJ, de Araujo-Filho PF, Bezerra JDM, Campelo DR. 2020. Adaptive packet padding approach for smart home networks: a tradeoff between privacy and performance. IEEE IoT-J, 8(5): 3930-3938.
- Sivanathan A, Gharakheili HH, Loi F, Radford A, Wijenayake C, Vishwanath A, Sivaraman V. 2018. Classifying IoT devices in smart environments using network traffic characteristics. IEEE TMC, 18(8): 1745-1759.
- Tolpegin V, Truex S, Gursoy ME, Liu L. 2020. Data poisoning attacks against federated learning systems. In: European Symposium on Research in Computer Security, 14-18 September 2020, Guildford, United Kingdom, pp: 480-501.
- Wang H, Xu P, Zhao J. 2021. Improved KNN algorithm based on preprocessing of center in smart cities. Complexity, 2021: 1-9.
- Yerlikaya FA, Bahtiyar Ş. 2022. Data poisoning attacks against machine learning algorithms. Expert Syst Appl, 208: 118101.
Ayrıntılar
| Birincil Dil | İngilizce |
|---|---|
| Konular | Bilgi Güvenliği Yönetimi, Bilgi Sistemleri (Diğer) |
| Bölüm | Research Articles |
| Yazarlar | |
| Proje Numarası | FM-HZP-2023-29550 |
| Yayımlanma Tarihi | 15 Mayıs 2024 |
| Gönderilme Tarihi | 1 Eylül 2023 |
| Kabul Tarihi | 26 Nisan 2024 |
| Yayımlandığı Sayı | Yıl 2024 Cilt: 7 Sayı: 3 |
