Towards a unified XAI-based framework for digital forensic investigations
Bibliographic record
Abstract
Explainable Artificial Intelligence (XAI) aims to alleviate the black-box AI conundrum in the field of Digital Forensics (DF) (and others) by providing layman-interpretable explanations to predictions made by AI models. It also handles the increasing volumes of forensic images that are impossible to investigate via manual methods; or even automated forensic tools. A holistic, generalized, yet exhaustive framework detailing the workflow of XAI for DF is proposed for standardization. A case study examining the implementation of the framework in a network forensics investigative scenario is presented for demonstration. In addition, the XAI-DF project lays the basis for a collaborative effort from the forensics community, aimed at creating an open-source forensic database that may be employed to train AI models for the digital forensics domain. As an onset contribution to the project, we create a memory forensics database of 27 memory dumps (Windows 7, 10, and 11) simulating malware activity and extracting relevant features (specific to processes, injected code, network connections, API hooks, and process privileges) that may be used for training, testing, and validating AI models in keeping with the XAI-DF framework.
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 | 0.011 | 0.014 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.004 |
| Bibliometrics | 0.007 | 0.003 |
| Science and technology studies | 0.002 | 0.005 |
| Scholarly communication | 0.012 | 0.008 |
| Open science | 0.007 | 0.008 |
| Research integrity | 0.003 | 0.006 |
| Insufficient payload (model declined to judge) | 0.006 | 0.003 |
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".