The International Arab Journal of Information Technology (IAJIT)


RoboGuard: Enhancing Robotic System Security with Ensemble Learning

Robots are becoming increasingly common in critical healthcare, transportation, and manufacturing applications. However, these systems are vulnerable to malware attacks, compromising reliability and security. Previous research has investigated the use of Machine Learning (ML) to detect malware in robots. However, existing approaches have faced several challenges, including class imbalance, high dimensionality, data heterogeneity, and balancing detection accuracy with false positives. This study introduces a novel approach to malware detection in robots that uses ensemble learning combined with the Synthetic Minority Over-sampling Technique (SMOTE). The proposed approach stacks three (ML models Random Forest (RF), Artificial Neural Networks (ANN), and Support Vector Machines (SVM) to improve accuracy and system robustness. SMOTE addresses the class imbalance in the dataset. Evaluation of the proposed approach on a publicly available dataset of robotic systems yielded promising results. The approach outperformed individual models and existing approaches regarding detection accuracy and false positive rates. This study represents a significant advancement in malware detection for robots. It could enhance the reliability and security of these systems in various critical applications.

[1] Akpinar K. and Ozcelik I., “Analysis of Machine Learning Methods in EtherCAT-Based Anomaly Detection,” IEEE Access, vol. 7, pp. 184365- RoboGuard: Enhancing Robotic System Security with Ensemble Learning 975 184374, 2019. DOI:10.1109/ACCESS.2019.2960497

[2] Alamer A. and Basudan S., “Security and privacy of Network Transmitted System in the Internet of Robotic Things,” The Journal of Supercomputing, vol. 78, no. 16, pp. 18361-18378, 2022. DOI:10.1007/s11227-022-04612-2

[3] Alheeti K., Al-Zaidi R., Woods J., and McDonald- Maier K., “An Intrusion Detection Scheme for Driverless Vehicles Based Gyroscope Sensor Profiling,” in Proceedings of the IEEE International Conference on Consumer Electronics, Las Vegas, pp. 448-449, 2017. DOI:10.1109/ICCE.2017.7889391

[4] Al-Slais Y. and Ali M., “Robotic Process Automation and Intelligent Automation Security Challenges: A Review,” in Proceedings of the International Conference on Cyber Management and Engineering, Bangkok, pp. 71-77, 2023. DOI:10.1109/CyMaEn57228.2023.10050996

[5] Breiman L., “Random Forests,” Machine Learning, vol. 45, pp. 5-32, 2001. 1010933404324.pdf

[6] Chawla N., Bowyer K., Hall L., and Kegelmeyer W., “SMOTE: Synthetic Minority Over-sampling Technique,” Journal of Artificial Intelligence Research, vol. 16, pp. 321-357, 2002.

[7] Clark G., Doran M., and Glisson W., “A Malicious Attack on the Machine Learning Policy of a Robotic System,” in Proceedings of the 17th IEEE International Conference on Trust, Security and Privacy in Computing and Communications/12th IEEE International Conference on Big Data Science and Engineering, New York, pp. 516-521, 2018. DOI:10.1109/TrustCom/BigDataSE.2018.00079

[8] Gao Y., Sun G., Liu J., Shi Y., and Wu L., “State Estimation and Self-Triggered Control of CPSs against Joint Sensor and Actuator Attacks,” Automatica, vol. 113, pp. 108687, 2020.

[9] Han S., Xie M., Chen H., and Ling Y., “Intrusion Detection in Cyber-Physical Systems: Techniques and Challenges,” IEEE Systems Journal, vol. 8, no. 4, pp. 1052-1062, 2014. DOI:10.1109/JSYST.2013.2257594

[10] Hector J., Katsiaris P., Carey N., Cote N., and Rawat D., “On the Security of Cyber-Physical Robotic Systems Using Dynamic Modeling and Simulation,” in Proceedings of the IEEE International Conference on Communications Workshops, Montreal, pp. 1-6, 2021. DOI:10.1109/ICCWorkshops50388.2021.947381 8

[11] Hong J., Liu C., and Govindarasu M., “Integrated Anomaly Detection for Cyber Security of the Substations,” IEEE Transactions on Smart Grid, vol. 5, no. 4, pp. 1643-1653, 2014. DOI:10.1109/TSG.2013.2294473

[12] Jiang J. and Chen Y., “Industrial Control System Anomaly Detection and Classification Based on Network Traffic,” IEEE Access, vol. 10, pp. 41874-41888, 2022. DOI:10.1109/ACCESS.2022.3167814

[13] Kaur U., Zhou H., Shen X., Min B., and Voyles R., “RoboMal: Malware Detection for Robot Network Systems,” in Proceedings of the 5th IEEE International Conference on Robotic Computing, Taichung, pp. 65-72, 2021. DOI:10.1109/IRC52146.2021.00016

[14] Khojasteh M., Khina A., Franceschetti M., and Javidi T., “Learning-Based Attacks in Cyber- Physical Systems,” IEEE Transactions on Control of Network Systems, vol. 8, no. 1, pp. 437-449, 2021. DOI:10.1109/TCNS.2020.3028035

[15] Koren I., “Detecting and Counteracting Benign Faults and Malicious Attacks in Cyber Physical Systems,” in Proceedings of the 7th Mediterranean Conference on Embedded Computing, Budva, pp. 2-2, 2018. DOI:10.1109/MECO.2018.8405951

[16] Li W., Xie L., and Wang Z., “Two-Loop Covert Attacks Against Constant Value Control of Industrial Control Systems,” IEEE Transactions on Industrial Informatics, vol. 15, no. 2, pp. 663- 676, 2019. DOI:10.1109/TII.2018.2819677

[17] Marchang J. and Di Nuovo A., “Assistive Multimodal Robotic System (AMRSys): Security and Privacy Issues, Challenges, and Possible Solutions,” Applied Sciences, vol. 12, no. 4, p. 2174, 2022.

[18] Martín F., Soriano E., and Canas J., “Quantitative Analysis of Security in Distributed Robotic Frameworks,” Robotics and Autonomous Systems, vol. 100, pp. 95-107, 2018.

[19] Maushart F., Prorok A., Hsieh M., and Kumar V., “Intrusion Detection for Stochastic Task Allocation in Robot Swarms,” in Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, Vancouver, pp. 1830-1837, 2017. DOI:10.1109/IROS.2017.8205998

[20] Mousavinejad E., Ge X., Han Q., Yang F., and Vlacic L., “Resilient Tracking Control of Networked Control Systems Under Cyber Attacks,” IEEE Transactions on Cybernetics, vol. 51, no. 4, pp. 2107-2119, 2021. DOI:10.1109/TCYB.2019.2948427

[21] Narayanan V. and Bobba R., “Learning Based Anomaly Detection for Industrial Arm Applications,” in Proceedings of the Workshop on Cyber-Physical Systems Security and PrivaCy, Toronto, pp. 13-23, 2018. 976 The International Arab Journal of Information Technology, Vol. 20, No. 6, November 2023

[22] Pawar K., Dharwadkar N., Deshpande P., Honawad S., and Dharmadhikari P., “An Android Based Smart Robotic Vehicle for Border Security Surveillance System,” in Proceedings of the 4th International Conference on Computational Intelligence and Communication Technologies, Sonepat, pp. 296-301, 2021. DOI: 10.1109/CCICT53244.2021.00062

[23] Pang Z., Liu G., Zhou D., Hou F., and Sun D., “Two-Channel False Data Injection Attacks against Output Tracking Control of Networked Systems,” IEEE Transactions on Industrial Electronics, vol. 63, no. 5, pp. 3242-3251, 2016. DOI: 10.1109/TIE.2016.2535119

[24] Pu H., He L., Cheng P., Sun M., and Chen J., “Security of Industrial Robots: Vulnerabilities, Attacks, and Mitigations,” IEEE Network, vol. 37, no. 1, pp. 111-117, 2023. DOI:10.1109/MNET.116.2200034

[25] Sharifi S., Usman M., and Gul E., “An Intelligent Health Control Security Robotic System,” University of Wah Journal of Computer Science, vol. 4, no. 1, pp. 17-30, 2022.

[26] Singh R., Kushwah A., Warrier P., and Oza S., “Wireless Surveillance Robot for Industrial Application,” in Proceedings of the Machine Learning, Image Processing, Network Security and Data Sciences: Select Proceedings of 3rd International Conference on MIND, Singapore, pp. 561-573, 2021. 981-19-5868-7_41

[27] Souza L., Rocha F., and Soares M., “A Review on Software/Systems Architecture Description for Autonomous Systems,” Recent Advances in Computer Science and Communications (Formerly: Recent Patents on Computer Science), vol. 16, no. 3, pp. 52-60, 2023. DOI:10.2174/2666255815666220513101350

[28] Sun Y., Shao H., and Zhang B, “Ensemble Based on Accuracy and Diversity Weighting for Evolving Data Streams,” The International Arab Journal of Information Technology, vol. 19, no. 1, pp. 90-96, 2022.

[29] Tang Y., Zhang D., Ho D., Yang W., and Wang B., “Event-Based Tracking Control of Mobile Robot with Denial-of-Service Attacks,” IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 50, no. 9, pp. 3300-3310, 2020. DOI:10.1109/TSMC.2018.2875793

[30] Zhao Z., Huang Y., Zhen Z., and Li Y., “Data- Driven False Data-Injection Attack Design and Detection in Cyber-Physical Systems,” IEEE Transactions on Cybernetics, vol. 51, no. 12, pp. 6179-6187, 2021. DOI:10.1109/TCYB.2020.2969320

[31] Zhou C., Hu B., Shi Y., Tian Y., Li X., and Zhao Y., “A Unified Architectural Approach for Cyberattack-Resilient Industrial Control Systems,” Proceedings of the IEEE, vol. 109, no. 4, pp. 517-541, 2021. DOI:10.1109/JPROC.2020.3034595

[32] Zhou C., Zhou C., Huang S., Xiong N., Yang S., Li H., Qin Y., and Li X., “Design and Analysis of Multimodel-Based Anomaly Intrusion Detection Systems in Industrial Process Automation,” IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 45, no. 10, pp. 1345-1360, 2015. DOI:10.1109/TSMC.2015.2415763