Using Counterfactuals for Explainable Android Malware Detection
Bibliographic record
Abstract
In the rapidly evolving landscape of smartphones and handheld devices, Android malware stands as a substantial security concern. Employing static analysis for mobile malware presents a proactive approach to understanding and unveiling potential threats within Android applications without the need for execution. Most of the existing studies on static analysis rely on machine learning. However, the black-box nature of machine learning models and their lack of explainability often hinder trust, transparency, and the ability to understand or justify their predictions. Counterfactual explanations enable security analysts to grasp the reasoning behind the decisions of black-box machine learning models (the “why?”) and also offer a way to pinpoint specific data instances whose alteration would lead to different prediction results (the “why not?”). In this paper, we investigate the use of the counterfactual explanation method to explain the predictions made by a machine learning model for Android malware classification. We assessed the quality of counterfactual explanations using a stability metric as well as investigating their feasibility by defining feature-based constraints.
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 | 0.035 | 0.236 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.004 |
| Bibliometrics | 0.006 | 0.002 |
| Science and technology studies | 0.002 | 0.007 |
| Scholarly communication | 0.005 | 0.009 |
| Open science | 0.003 | 0.004 |
| Research integrity | 0.003 | 0.004 |
| Insufficient payload (model declined to judge) | 0.005 | 0.000 |
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".