Seeing without Looking: Analysis Pipeline for Child Sexual Abuse Datasets
| dc.contributor.author | Laranjeira, C., Macedo, J., Avila, S., & Santos, J. A. D. | |
| dc.date.accessioned | 2022-05-11T18:40:09Z | |
| dc.date.available | 2022-05-11T18:40:09Z | |
| dc.date.issued | 2022 | |
| dc.description.abstract | The online sharing and viewing of Child Sexual Abuse Material (CSAM) are growing fast, such that human experts can no longer handle the manual inspection. However, the automatic classification of CSAM is a challenging field of research, largely due to the inaccessibility of target data that is — and should forever be — private and in sole possession of law enforcement agencies. To aid researchers in drawing insights from unseen data and safely providing further understanding of CSAM images, we propose an analysis template that goes beyond the statistics of the dataset and respective labels. It focuses on the extraction of automatic signals, provided both by pre-trained machine learning models, e.g., object categories and pornography detection, as well as image metrics such as luminance and sharpness. Only aggregated statistics of sparse signals are provided to guarantee the anonymity of children and adolescents victimized. The pipeline allows filtering the data by applying thresholds to each specified signal and provides the distribution of such signals within the subset, correlations between signals, as well as a bias evaluation. We demonstrated our proposal on the Region-based annotated Child Pornography Dataset (RCPD), one of the few CSAM benchmarks in the literature, composed of over 2000 samples among regular and CSAM images, produced in partnership with Brazil’s Federal Police. Although noisy and limited in several senses, we argue that automatic signals can highlight important aspects of the overall distribution of data, which is valuable for databases that can not be disclosed. Our goal is to safely publicize the characteristics of CSAM datasets, encouraging researchers to join the field and perhaps other institutions to provide similar reports on their benchmark | en_US |
| dc.identifier.citation | Laranjeira, C., Macedo, J., Avila, S., & Santos, J. A. D. (2022). Seeing without Looking: Analysis Pipeline for Child Sexual Abuse Datasets. arXiv preprint arXiv:2204.14110. | en_US |
| dc.identifier.uri | https://arxiv.org/pdf/2204.14110.pdf | |
| dc.identifier.uri | http://hdl.handle.net/11212/5416 | |
| dc.language.iso | en | en_US |
| dc.publisher | Association for Computing Machinery | en_US |
| dc.subject | child sexual abuse material | en_US |
| dc.subject | International Resources | en_US |
| dc.subject | Brazil | en_US |
| dc.subject | transparency | en_US |
| dc.subject | bias | en_US |
| dc.subject | sensitive media | en_US |
| dc.title | Seeing without Looking: Analysis Pipeline for Child Sexual Abuse Datasets | en_US |
| dc.type | Article | en_US |