Systematic Mapping of Machine Learning–Based Malware Detection Studies
Bibliographic record
Abstract
The threat of computer malware and viruses is an ever-growing threat in today’s technological age. While the use of common anti-virus programs help limit the issue of having a computer infected with malware, the types and frequency of these viruses continue to rise and evolve at an uncontrollable rate. In order to combat this issue, the implementation of machine learning algorithms must continue to rise and evolve to fight and prevent a wide selection of malware. In this study, we are presenting our findings from a systematic mapping (SM) review of research in this area to determine the main factors that go into the testing and detection development of said research. These factors include the types of malware being tested, the machine learning algorithms used, among others. To determine these factors, we analyze a selection of articles from a literature database search query. This search, limited between the start of 2017 to the end of March 2022, resulted in 254 studies conducted in the scientific literature space. After conducting a multi-phase review of those studies, a subset of 28 papers were selected for further analysis. The results obtained from applying the systematic mapping process indicate that the testing of machine learning has a range of potential benefits, but has significant potential for improvement in future research.
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 | 0.043 | 0.233 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.006 | 0.007 |
| Bibliometrics | 0.073 | 0.038 |
| Science and technology studies | 0.002 | 0.002 |
| Scholarly communication | 0.005 | 0.005 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 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".