Automatyczne rozpoznawanie treści nielegalnych filmów typu CSAM za pomocą klasyfikatora częściowo splatającego kolejne klatki materiału wideo
More details
Hide details
Zespół Złożonych Systemów, Instytut Automatyki i Informatyki Stosowanej, Wydział Elektroniki i Technik Informacyjnych, Politechnika Warszawska
Publication date: 2023-10-31
Cybersecurity and Law 2023;10(2):195-201
The paper describes one of the methods of automatic recognition of CSAM materials, which was tested during the research under the APAKT project. The proposed solution is based on Temporal Shift Module (TSM), a model of a deep neural network created for efficient human activities rocognition in video. We applied transfer learning method for training the model with a relatively small number of training data to succesfully rocognize films with pornografic and illegal content. We conducted some tests of classification of films from three categories: neutral films, legal pornography and illegal pornografic videos (CSAM). In this paper we present problems that are connected with this research topic that come from the characteristic of the data. We also show that further works are needed to keep children safe in cyberspace.
Aggarwal Ch.C., Neural Networks and Deep Learning, Cham 2018.
Badźmirowska-Masłowska K., Child protection in cyberspace, „Cybersecurity and Law” 2019, nr 1.
Lin J., Gan C., Han S., TSM: Temporal Shift Module for Efficient Video Understanding, 2018, https://doi.org/10.48550/arXiv... [dostęp: 15.06.2023].
Kay W. i in., The Kinetics Human Action Video Dataset, 2017, https://doi.org/10.48550/arXiv... [dostęp: 15.06.2023].
Koonce B., ResNet 50 [w:]: Convolutional Neural Networks with Swift for Tensorflow, Berkeley, CA 2021.
Journals System - logo
Scroll to top