South Korea has a dark history of digital sex crimes. In 2019 it emerged that men were using a Telegram chatroom to blackmail dozens of young women into performing sexual acts, in a scandal known as nth-room. The group's ring-leader, Cho Ju-bin, was sentenced to 42 years in jail. Online deepfake sex crimes have surged, according to South Korean police. A total of 297 cases were reported in the first seven months of this year, up from 180 in the whole of last year and 160 in 2021.

In social network service platforms, crime suspects are likely to use cybercrime coded words for communication by adding criminal meanings to existing words or replacing them with similar words. For instance, the word 'ice' is often used to mean methamphetamine in drug crimes. To analyze the nature of cybercrime and the behavior of criminals, quickly detecting such words and further understanding their meaning are critical. In the automated cybercrime coded word detection problem, it is difficult to collect a sufficient amount of training data for supervised learning and to directly apply language models that utilize context information to better understand natural language. To overcome these limitations, we propose a new two-step approach, in which a mean latent vector is constructed for each cybercrime through one of five different AutoEncoder models in the first step, and cybercrime coded words are detected based on multi-level latent representations in the second step. Moreover, to deeply understand cybercrime coded words detected through the two-step approach, we propose three novel methods: (1) Detection of new words recently coined, (2) Detection of words frequently appeared in both drug and sex crimes, and (3) Automatic generation of word taxonomy. According to our experimental results, among various AutoEncoder models, the stacked AutoEncoder model shows the best performance. Additionally, the F1-score of the two-step approach is 0.991, which is higher than 0.987 and 0.903 of the existing dark-GloVe and dark-BERT models. By analyzing the experimental results of the three proposed methods, we can gain a deeper understanding of drug and sex crimes.

A record 889 people under 18 fell victim to sex crimes and other offenses perpetrated via social networking services from January to June, the National Police Agency said Thursday. The number is 33 higher than the tally from July to December last year, marking the highest level since data on a half-year basis became available in 2008. As a breeding ground for sex crimes, Twitter and other largely unregulated SNS sites overtook dating sites, which are bound by regulations including a minimum age rule of 18, analysts said. Of the total, 348, or 40 percent, fell prey to indecent acts, 268 to child pornography and 225 to prostitution. Eight children, including some as young as 11, were raped, and 13 abducted.