Detecção de Ataques de Injeção de Dados no Tráfego de Rede de Sistemas ROS
Resumo
O Robot Operating System (ROS) é um dos mais populares softwares voltados ao desenvolvimento e pesquisa em robótica. Entretanto, estudos têm demonstrado diversos problemas de segurança em sua estrutura. Este trabalho avalia a aplicação de técnicas de detecção de intrusão no reconhecimento de ataques de injeção de dados nesses sistemas. Um modelo foi proposto, empregando um algoritmo de máquinas de vetores de suporte, o qual foi treinado a partir de características do tráfego de rede de uma aplicação ROS. Resultados preliminares mostraram uma acurácia de cerca de 92%.
Palavras-chave:
Robótica, ROS, Segurança, Detecção de intrusão, Aprendizado de máquina
Referências
Amrouche, F., Lagraa, S., Frank, R., and State, R. (2020). Intrusion detection on robot cameras using spatio-temporal autoencoders: A self-driving car application. In 2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring), pages 1–5. IEEE.
Breiling, B., Dieber, B., and Schartner, P. (2017). Secure communication for the robot operating system. In 2017 annual IEEE international systems conference (SysCon), pages 1–6. IEEE.
Chang, C.-C. and Lin, C.-J. (2011). Libsvm: a library for support vector machines. ACM transactions on intelligent systems and technology (TIST), 2(3):1–27.
Dieber, B., Breiling, B., Taurer, S., Rass, S., and Schartner, P. (2017). Security for the robot operating system. Robotics and Autonomous Systems, 98:192–203.
Hsu, C.-W. and Chang, C.-C. (2003). A practical guide to support vector classification.
Mayoral-Vilches, V., Pinzger, M., Rass, S., Dieber, B., and Gil-Uriarte, E. (2020). Can ros be used securely in industry? red teaming ros-industrial. arXiv preprint arXiv:2009.08211.
Mohammadi Rouzbahani, H., Karimipour, H., Rahimnejad, A., Dehghantanha, A., and Srivastava, G. (2020). Anomaly Detection in Cyber-Physical Systems Using Machine Learning, pages 219–235. Springer International Publishing, Cham.
Narayanan, V. and Bobba, R. B. (2018). Learning based anomaly detection for industrial arm applications. In Proceedings of the 2018 Workshop on Cyber-Physical Systems Security and PrivaCy, pages 13–23.
Rivera, S. and State, R. (2021). Securing robots: An integrated approach for security challenges and monitoring for the robotic operating system (ros). In 2021 IFIP/IEEE International Symposium on Integrated Network Management (IM), pages 754–759.
Teixeira, R. R., Maurell, I. P., and Drews, P. L. (2020). Security on ros: analyzing and exploiting vulnerabilities of ros-based systems. In 2020 Latin American Robotics Symposium (LARS), 2020 Brazilian Symposium on Robotics (SBR) and 2020 Workshop on Robotics in Education (WRE), pages 1–6. IEEE.
Vasquez, G., Miani, R. S., and Zarpelao, B. B. (2017). Flow-based intrusion detection for scada networks using supervised learning. XVII Simp´osio Brasileiro em Seguranca da Informacao e de Sistemas, pages 168–181.
Breiling, B., Dieber, B., and Schartner, P. (2017). Secure communication for the robot operating system. In 2017 annual IEEE international systems conference (SysCon), pages 1–6. IEEE.
Chang, C.-C. and Lin, C.-J. (2011). Libsvm: a library for support vector machines. ACM transactions on intelligent systems and technology (TIST), 2(3):1–27.
Dieber, B., Breiling, B., Taurer, S., Rass, S., and Schartner, P. (2017). Security for the robot operating system. Robotics and Autonomous Systems, 98:192–203.
Hsu, C.-W. and Chang, C.-C. (2003). A practical guide to support vector classification.
Mayoral-Vilches, V., Pinzger, M., Rass, S., Dieber, B., and Gil-Uriarte, E. (2020). Can ros be used securely in industry? red teaming ros-industrial. arXiv preprint arXiv:2009.08211.
Mohammadi Rouzbahani, H., Karimipour, H., Rahimnejad, A., Dehghantanha, A., and Srivastava, G. (2020). Anomaly Detection in Cyber-Physical Systems Using Machine Learning, pages 219–235. Springer International Publishing, Cham.
Narayanan, V. and Bobba, R. B. (2018). Learning based anomaly detection for industrial arm applications. In Proceedings of the 2018 Workshop on Cyber-Physical Systems Security and PrivaCy, pages 13–23.
Rivera, S. and State, R. (2021). Securing robots: An integrated approach for security challenges and monitoring for the robotic operating system (ros). In 2021 IFIP/IEEE International Symposium on Integrated Network Management (IM), pages 754–759.
Teixeira, R. R., Maurell, I. P., and Drews, P. L. (2020). Security on ros: analyzing and exploiting vulnerabilities of ros-based systems. In 2020 Latin American Robotics Symposium (LARS), 2020 Brazilian Symposium on Robotics (SBR) and 2020 Workshop on Robotics in Education (WRE), pages 1–6. IEEE.
Vasquez, G., Miani, R. S., and Zarpelao, B. B. (2017). Flow-based intrusion detection for scada networks using supervised learning. XVII Simp´osio Brasileiro em Seguranca da Informacao e de Sistemas, pages 168–181.
Publicado
12/09/2022
Como Citar
ANTUNES, Rodrigo; DALMAZO, Bruno L.; DREWS, Paulo.
Detecção de Ataques de Injeção de Dados no Tráfego de Rede de Sistemas ROS. In: SIMPÓSIO BRASILEIRO DE SEGURANÇA DA INFORMAÇÃO E DE SISTEMAS COMPUTACIONAIS (SBSEG), 22. , 2022, Santa Maria.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2022
.
p. 384-389.
DOI: https://doi.org/10.5753/sbseg.2022.223942.
