Keystroke Dynamics through the Prism of Digital Criminalistics
Bibliographic record
Abstract
This work seeks to substantiate that keystroke dynamics (typing pattern) falls within the subject matter of digital criminalistics. To achieve this aim, the Author employs an interdisciplinary approach, methods of synthesis and analysis, as well as analogy and modeling, which make it possible to project general features onto a specific frequent phenomenon of modern reality. The work consistently characterizes the phenomenon of keystroke dynamics, raises general issues of digital criminalistics, identifies the features of digital traces, and compares them with the phenomenon of keystroke dynamics. An authorial definition of keystroke dynamics is provided, and the need to intensify its forensic study is emphasized so as to enhance the effectiveness of efforts to detect and investigate crimes where accurate identification of the typist matters (dissemination of extremist messages, preparatory criminal activity on online platforms, creation of “death groups,” etc.). Debated issues of digital criminalistics as a new subdiscipline are considered. The positions of various authors are analyzed regarding the name of the field, the terminological designation of traces studied, and the determination of their nature, and the Author’s own position is substantiated. Specific features of digital traces (material yet mediated character, belonging to computer information, remote accessibility, copyability, abstractness, etc.) are highlighted, and the correspondence of keystroke dynamics to these features is demonstrated—keystroke dynamics being a special typing skill that finds reflection in system logs on a computer or in the memory of specialized technical devices. The study confirms the initial scientific hypothesis: when recorded in the memory of a computer or a specialized device, keystroke dynamics falls within the subject area of digital criminalistics, as it is a digital trace and, in this capacity, can be used to solve crime-control tasks. Its study should become an alternative to traditional handwriting examinations in today’s conditions of transition to electronic document flow and digital communication.
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 | 0.010 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.006 | 0.003 |
| Science and technology studies | 0.003 | 0.014 |
| Scholarly communication | 0.009 | 0.011 |
| Open science | 0.001 | 0.007 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 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".