An efficient method to detect series of fraudulent identity documents based on digitised forensic data
Bibliographic record
Abstract
Document fraud is a transnational form of crime, and its serial character has already been highlighted. To combat this phenomenon, the Interstate Database of Fraudulent Identity Documents (BIDIF) has been created and implemented in Switzerland. It supports the comparison of documents and the detection of series, i.e., documents that share a common source. To efficiently use such a system, forensic document examiners would benefit from a harmonised and proven profiling method. Thus, the aim of this study is to develop a method for comparing documents and establishing series. The method is meant to improve the detection capabilities of forensic document examiners operating BIDIF or engaged in the profiling of fraudulent documents. First, a method based on the visual characteristics of digitised images of fraudulent identity documents has been developed. Subsequently, the method was qualitatively and quantitatively evaluated using four tests. The first test verified the ability of the method to detect pre-existing series. The second test checked the capability of the method to detect links amongst isolated documents. Finally, two further tests were carried out to compare the method impact on the successful detection of series. These tests were carried out by professional forensic document examiners and Master students in forensic science, respectively. This allowed a comparison of the method influence on series detection. The method allowed a significant increase in the number of series and links detected, while also decreasing the occurrence of false negatives and false positives. Furthermore, links were more rapidly detected.
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 | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.010 | 0.003 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".