Clasificación de capturas de smishing con aprendizaje profundo e IRIS

  1. Blanco Medina, Pablo 1
  2. Carofilis, Andrés 1
  3. Fidalgo, Eduardo 1
  4. Alegre, Enrique 1
  1. 1 Universidad de León
    info

    Universidad de León

    León, España

    ROR https://ror.org/02tzt0b78

Revista:
Jornadas de Automática
  1. Cruz Martín, Ana María (coord.)
  2. Arévalo Espejo, V. (coord.)
  3. Fernández Lozano, Juan Jesús (coord.)

ISSN: 3045-4093

Año de publicación: 2024

Número: 45

Tipo: Artículo

DOI: 10.17979/JA-CEA.2024.45.10904 DIALNET GOOGLE SCHOLAR lock_openAcceso abierto editor

Resumen

Smishing, a variant of phishing that uses the Short Message Service, uses smartphones and the trust of people in text messaging as a communication tool to spread more easily. When citizens report these suspicious messages to Computer Emergency Response Teams, they usually do it through a screenshot of their smartphone. Response Teams may find useful an automatic tool that classifies Smishing into different categories before proceeding to further information extraction. We propose to compare the performance of customized Convolutional Neural Networks and Vision Transformers with their pre-trained versions on ImageNet datasets for automatically classifying smishing screenshots into two different categories: joint and separate text. We make publicly available a novel dataset, IRIS-244, containing 244 smishing screenshots with phishing URLs. Combined with data augmentation techniques, we discovered that Xception architecture out performs the rest of the approaches, with an accuracy score of 78,36.

Referencias bibliográficas

  • Akande, O. N., Gbenle, O., Abikoye, O. C., Jimoh, R. G., Akande, H. B., Balogun, A. O., Fatokun, A., 2023. Smsprotect: An automatic smishing detection mobile application. ICT Express 9 (2), 168–176. DOI: https://doi.org/10.1016/j.icte.2022.05.009
  • Bai, Y., Mei, J., Yuille, A. L., Xie, C., 2021. Are transformers more robust than cnns? Advances in neural information processing systems 34, 26831– 26843.
  • Blanco-Medina, P., Fidalgo, E., Alegre, E., Vasco-Carofilis, R. A., Janez-Martino, F., Villar, V. F., 2021. Detecting vulnerabilities in critical infras- tructures by classifying exposed industrial control systems using deep lear- ning. Applied Sciences 11 (1), 367. DOI: https://doi.org/10.3390/app11010367
  • Chollet, F., 2017. Xception: Deep learning with depthwise separable convo- lutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 1251–1258. DOI: https://doi.org/10.1109/CVPR.2017.195
  • Chollet, F., et al., 2015. Keras. https://keras.io.
  • Coquenet, D., Chatelain, C., Paquet, T., 2023. Dan: a segmentation-free document attention network for handwritten document recognition. IEEE transactions on pattern analysis and machine intelligence. DOI: https://doi.org/10.1109/TPAMI.2023.3235826
  • Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Un- terthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al., 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929.
  • Fidalgo, E., Alegre, E., Gonzalez-Castro, V., Fernández-Robles, L., 2018. Boosting image classification through semantic attention filtering strategies. Pattern Recognition Letters 112, 176–183. DOI: https://doi.org/10.1016/j.patrec.2018.06.033
  • Gangwar, A., Gonza ́lez-Castro, V., Alegre, E., Fidalgo, E., 2021. Attm-cnn: Attention and metric learning based cnn for pornography, age and child sexual abuse (csa) detection in images. Neurocomputing 445, 81–104. DOI: https://doi.org/10.1016/j.neucom.2021.02.056
  • Kumarasiri, W., Siriwardhana, M., Suraweera, S., Senarathne, A., Harsha- nath, S., 2023. Cybersmish: A proactive approach for smishing detection and prevention using machine learning. In: 2023 7th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud)(I-SMAC). IEEE, pp. 210–217. DOI: https://doi.org/10.1109/I-SMAC58438.2023.10290228
  • Liu, Z., Mao, H., Wu, C.-Y., Feichtenhofer, C., Darrell, T., Xie, S., 2022. A convnet for the 2020s. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. pp. 11976–11986. DOI: https://doi.org/10.1109/CVPR52688.2022.01167
  • Maurício, J., Domingues, I., Bernardino, J., 2023. Comparing vision transformers and convolutional neural networks for image classification: A litera- ture review. Applied Sciences 13 (9), 5521. DOI: https://doi.org/10.3390/app13095521
  • Mishra, S., Soni, D., 2023. Dsmishsms-a system to detect smishing sms. Neural Computing and Applications 35 (7), 4975–4992. DOI: https://doi.org/10.1007/s00521-021-06305-y
  • Pal, K., Patel, B. V., 2020. Data classification with k-fold cross validation and holdout accuracy estimation methods with 5 different machine lear- ning techniques. In: 2020 fourth international conference on computing methodologies and communication (ICCMC). IEEE, pp. 83–87. DOI: https://doi.org/10.1109/ICCMC48092.2020.ICCMC-00016
  • Rahman, M. L., Timko, D., Wali, H., Neupane, A., 2023. Users really do respond to smishing. In: Proceedings of the Thirteenth ACM Conference on Data and Application Security and Privacy. pp. 49–60. DOI: https://doi.org/10.1145/3577923.3583640
  • Recht, B., Roelofs, R., Schmidt, L., Shankar, V., 2019. Do imagenet classifiers generalize to imagenet? In: International conference on machine learning. PMLR, pp. 5389–5400.
  • Shorten, C., Khoshgoftaar, T. M., 2019. A survey on image data augmentation for deep learning. Journal of big data 6 (1), 1–48. DOI: https://doi.org/10.1186/s40537-019-0197-0
  • Ulfath, R. E., Sarker, I. H., Chowdhury, M. J. M., Hammoudeh, M., 2022. Detecting smishing attacks using feature extraction and classification techniques. In: Proceedings of the International Conference on Big Data, IoT, and Machine Learning: BIM 2021. Springer, pp. 677–689. DOI: https://doi.org/10.1007/978-981-16-6636-0_51