System wspomagający wykrywanie treści wizualnych i tekstowych zagrażających bezpieczeństwu dzieci w cyberprzestrzeni

In recent years, there has been a significant increase in threats to children’s safety in cyberspace. The most serious of these include children’s participation in illegal online activities and the production of sexually explicit content involving them. Therefore, it is of fundamental importance to build awareness of cyber threats among our society’s youngest members and teach them skills for the safe use of products and services assigned to cyberspace. A key action for effectively protecting children in this environment is the early detection and reporting to the relevant authorities of illegal behavior and child abuse content. Teams such as Dyżurnet.pl, whose tasks currently include responding to potentially illegal content reported by cyberspace users, and in the near future, possibly also conducting proactive activities in this area, play an important role here. The experience of Dyżurnet.pl clearly shows that effective detection of such content requires automation of activities and appropriate IT tools. This paper presents a novel network monitoring and decision support system using artificial intelligence methods, including deep learning, to automatically detect potentially harmful material, such as Child Sexual Abuse Material (CSAM), erotic content involving children, pornographic content with a created or processed image of a child and pornography involving adults.