Ensemble Machine Learning Models Utilizing a Hybrid Recursive Feature Elimination (RFE) Technique for Detecting GPS Spoofing Attacks Against Unmanned Aerial Vehicles
Bibliographic record
Abstract
The dependency of Unmanned Aerial Vehicles (UAVs), also known as drones, on off-board data, such as control and position data, makes them highly susceptible to serious safety and security threats, including data interceptions, Global Positioning System (GPS) jamming, and spoofing attacks. This indeed necessitates the existence of an Intrusion Detection System (IDS) in place to detect potential security threats/intrusions promptly. Recently, machine-learning-based IDSs have gained popularity due to their high performance in detecting known as well as novel cyber-attacks. However, the time and computation efficiencies of ML-based IDSs still present a challenge in the UAV domain. Therefore, this paper proposes a hybrid Recursive Feature Elimination (RFE) technique based on feature importance ranking along with a Spearman Correlation Analysis (SCA). This technique is built on ensemble learning approaches, namely, bagging, boosting, stacking, and voting classifiers, to efficiently detect GPS spoofing attacks. Two benchmark datasets are employed: the GPS spoofing dataset and the UAV location GPS spoofing dataset. The results show that our proposed ensemble models achieved a notable balance between efficacy and efficiency, showing that the bagging classifier achieved the highest accuracy rate of 99.50%. At the same time, the Decision Tree (DT) and the bagging classifiers achieved the lowest processing time of 0.003 s and 0.029 s, respectively, using the GPS spoofing dataset. For the UAV location GPS spoofing dataset, the bagging classifier emerged as the top performer, achieving 99.16% accuracy and 0.002 s processing time compared to other well-known ML models. In addition, the experimental results show that our proposed methodology (RFE) outperformed other well-known ML models built on conventional feature selection techniques for detecting GPS spoofing attacks, such as mutual information gain, correlation matrices, and the chi-square test.
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) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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".