Safe-Uav: An Explainable AI-assisted Framework for Securing UAV Communication Networks
Bibliographic record
Abstract
Technology is progressing, leading to the widespread adoption of Unmanned Aerial Vehicles (UAVs) in multiple industries. Nevertheless, security remains the top priority, especially when it comes to identifying and stopping drone attacks. This paper suggests using machine learning and ensemble learning in system model to effectively detect and prevent attacks before they happen. A major obstacle is reducing both false positives and false negatives, since incorrectly identifying valid nodes as intruders, or vice versa, can impact the security system’s efficiency. In response to this issue, the paper presents a Safe-Uav framework for detecting and categorizing attacks, using XGBoost, which achieves an accuracy of 92.87% as well as strong precision, F1 score, and recall measures. Moreover, the research utilizes LIME and SHAP, important tools in XAI, to improve the transparency and reliability of the model’s forecasts. LIME focuses on explaining the model’s actions for individual cases, while SHAP provides consistent explanations rooted in Shapley values. This mix of advanced detection methods and interpretability tools enhances the transparency and dependability of the Safe-Uav 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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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".