Comparing Methods for Detecting Child Exploitation Content Online
Bibliographic record
Abstract
The sexual exploitation of children online is seen as a global issue and has been addressed by both governments and private organizations. Efforts thus far have focused primarily on the use of image hash value databases to find content. However, recently researchers have begun to use keywords as a way to detect child exploitation content. Within the current study we explore both of these methodologies. Using a custom designed web-crawler, we create three networks using the hash value method, keywords method, and a hybrid method combining the first two. Results first show that the three million images found in our hash value database were not common enough on public websites for the hash value method to produce meaningful result. Second, the small sample of websites that were found to contain those images had little to no videos posted, suggesting a need for different criteria for finding each type of material. Third, websites with code words commonly known to be used by child pornographers to identify or discuss exploitative content, were found to be much larger than others, with extensive visual and textual content. Finally, boy-centered keywords were more commonly found on child exploitation websites than girl-centered keywords, though not at a statistically significant level. Applications for law enforcement and areas for future research are discussed.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.009 | 0.030 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.015 | 0.005 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.004 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".