Avaliação das CGANs na Robustez de Modelos de Classificação de Ataques em IoT
Resumo
Este artigo avalia o uso de Redes Geradoras Adversárias Condicionais (do inglês, Conditional Generative Adversarial Networks – CGANs) na classificação de ciberataques em redes da Intenet das Coisas (IoT). Diferentemente das GANs tradicionais, as CGANs incorporam rótulos — como informações de fluxo de rede — no processo de geração de amostras, permitindo a criação de amostras adversariais mais direcionadas e realistas. Essas amostras geradas imitam os dados reais e são utilizadas para testar a resiliência de classificadores de ataques, ao tentar induzi-los ao erro. O estudo analisa como essas amostras adversariais impactam a robustez dos modelos e propõe uma abordagem de treinamento adversarial, na qual as amostras geradas pelas CGANs são integradas ao processo de treinamento para melhorar o desempenho do classificador. Os experimentos foram realizados com dois conjuntos de dados amplamente utilizados na área – IoT-23 e TON-IoT – e avaliados com base em métricas como acurácia e precisão.
Palavras-chave:
Ataques Adversariais, Aprendizado de Máquina Adversarial, Cibersegurança, Inteligência Artificial, Rede Adversarial Generativa Condicional, Tráfego de Redes IoT
Referências
Alsaedi, A., Moustafa, N., Tari, Z., Mahmood, A., and Anwar, A. (2020). Ton-IoT telemetry dataset: A new generation dataset of IoT and IIoT for data-driven intrusion detection systems. IEEE Access, 8, 165130–165150.
Apruzzese, G., Colajanni, M., Ferretti, L., and Marchetti, M. (2019). Addressing adversarial attacks against security systems based on machine learning. In International Conference on Cyber Conflict (CyCon), volume 900, pages 1–18.
Ayub, M. A., Johnson, W. A., Talbert, D. A., and Siraj, A. (2020). Model evasion attack on intrusion detection systems using adversarial machine learning. In Annual Conference on Information Sciences and Systems (CISS), pages 1–6. IEEE.
Chauhan, R. and Heydari, S. S. (2020). Polymorphic adversarial DDoS attack on IDS using GAN. In 2020 International Symposium on Networks, Computers and Communications (ISNCC), pages 1–6. IEEE.
Chen, L., Ye, Y., and Bourlai, T. (2017). Adversarial machine learning in malware detection: Arms race between evasion attack and defense. In 2017 European Intelligence and Security Informatics Conference (EISIC), pages 99–106.
Dunmore, A., Jang-Jaccard, J., Sabrina, F., and Kwak, J. (2023). A comprehensive survey of generative adversarial networks (GANs) in cybersecurity intrusion detection. IEEE Access, 11, 76071–76094.
Garcia, S., Parmisano, A., and Erquiaga, M. J. (2020). IoT-23: A labeled dataset with malicious and benign IoT network traffic.
Géron, A. (2022). Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: Concepts, tools, and techniques to build intelligent systems. O’Reilly Media, Inc.
Kemmerer, R. A. (2003). Cybersecurity. In International Conference on Software Engineering, 2003. Proceedings., pages 705–715. IEEE.
Kuppa, A. and Le-Khac, N.-A. (2021). Adversarial XAI methods in cybersecurity. IEEE Transactions on Information Forensics and Security, 16, 4924–4938.
Lin, Z., Shi, Y., and Xue, Z. (2022). IDSGAN: Generative Adversarial Networks for attack generation against intrusion detection. In Advances in Intelligent Systems and Computing, pages 79–91. Springer International Publishing.
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., and Vladu, A. (2019). Towards deep learning models resistant to adversarial attacks.
McCarthy, A., Ghadafi, E., Andriotis, P., and Legg, P. (2023). Defending against adversarial machine learning attacks using hierarchical learning: A case study on network traffic attack classification. Journal of Information Security and Applications, 72, 103398.
Mirza, M. and Osindero, S. (2014). Conditional generative adversarial nets.
Randhawa, R. H., Aslam, N., Alauthman, M., Rafiq, H., and Comeau, F. (2021). Security hardening of botnet detectors using generative adversarial networks. IEEE Access, 9, 78276–78292.
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., and Fergus, R. (2014). Intriguing properties of neural networks.
Ullah, I. and Mahmoud, Q. H. (2021). A framework for anomaly detection in IoT networks using conditional generative adversarial networks. IEEE Access, 9, 165907–165931.
Apruzzese, G., Colajanni, M., Ferretti, L., and Marchetti, M. (2019). Addressing adversarial attacks against security systems based on machine learning. In International Conference on Cyber Conflict (CyCon), volume 900, pages 1–18.
Ayub, M. A., Johnson, W. A., Talbert, D. A., and Siraj, A. (2020). Model evasion attack on intrusion detection systems using adversarial machine learning. In Annual Conference on Information Sciences and Systems (CISS), pages 1–6. IEEE.
Chauhan, R. and Heydari, S. S. (2020). Polymorphic adversarial DDoS attack on IDS using GAN. In 2020 International Symposium on Networks, Computers and Communications (ISNCC), pages 1–6. IEEE.
Chen, L., Ye, Y., and Bourlai, T. (2017). Adversarial machine learning in malware detection: Arms race between evasion attack and defense. In 2017 European Intelligence and Security Informatics Conference (EISIC), pages 99–106.
Dunmore, A., Jang-Jaccard, J., Sabrina, F., and Kwak, J. (2023). A comprehensive survey of generative adversarial networks (GANs) in cybersecurity intrusion detection. IEEE Access, 11, 76071–76094.
Garcia, S., Parmisano, A., and Erquiaga, M. J. (2020). IoT-23: A labeled dataset with malicious and benign IoT network traffic.
Géron, A. (2022). Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: Concepts, tools, and techniques to build intelligent systems. O’Reilly Media, Inc.
Kemmerer, R. A. (2003). Cybersecurity. In International Conference on Software Engineering, 2003. Proceedings., pages 705–715. IEEE.
Kuppa, A. and Le-Khac, N.-A. (2021). Adversarial XAI methods in cybersecurity. IEEE Transactions on Information Forensics and Security, 16, 4924–4938.
Lin, Z., Shi, Y., and Xue, Z. (2022). IDSGAN: Generative Adversarial Networks for attack generation against intrusion detection. In Advances in Intelligent Systems and Computing, pages 79–91. Springer International Publishing.
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., and Vladu, A. (2019). Towards deep learning models resistant to adversarial attacks.
McCarthy, A., Ghadafi, E., Andriotis, P., and Legg, P. (2023). Defending against adversarial machine learning attacks using hierarchical learning: A case study on network traffic attack classification. Journal of Information Security and Applications, 72, 103398.
Mirza, M. and Osindero, S. (2014). Conditional generative adversarial nets.
Randhawa, R. H., Aslam, N., Alauthman, M., Rafiq, H., and Comeau, F. (2021). Security hardening of botnet detectors using generative adversarial networks. IEEE Access, 9, 78276–78292.
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., and Fergus, R. (2014). Intriguing properties of neural networks.
Ullah, I. and Mahmoud, Q. H. (2021). A framework for anomaly detection in IoT networks using conditional generative adversarial networks. IEEE Access, 9, 165907–165931.
Publicado
19/05/2025
Como Citar
PEREIRA, Fernanda C. S.; PELLOSO, Mateus; NOGUEIRA, Michele.
Avaliação das CGANs na Robustez de Modelos de Classificação de Ataques em IoT. In: WORKSHOP DE GERÊNCIA E OPERAÇÃO DE REDES E SERVIÇOS (WGRS), 30. , 2025, Natal/RN.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 1-14.
ISSN 2595-2722.
DOI: https://doi.org/10.5753/wgrs.2025.7536.
