Zero-Day Gps Attack Detection and Classification in Uav Networks
Bibliographic record
Abstract
Unmanned aerial vehicles (UAVs) face escalating cybersecurity threats, particularly from GPS spoofing and jamming attacks, which endanger flight safety and mission integrity. This paper introduces a novel UAV cybersecurity framework that integrates statistical extreme value meta-learning (EVML) with a dual-path classifier to detect and classify GPS attacks. The method overcomes the key limitations of some existing approaches, such as excessive training data needs, zero-day threat vulnerability, and disjointed detection/classification. In particular, the proposed framework includes two stages. The first one enables zero-day attack detection through few-shot meta-learning with prototype-based anomaly detection where support sets contain only benign flight data while query sets include both benign samples and synthetically generated attack patterns. Moreover, a prototypical OpenMax layer and extreme value theory are exploited to identify suspicious patterns in GPS telemetry data. The second stage utilizes a novel dual-path architecture that independently processes position-related and signal-related features to classify detected attacks as spoofing or jamming. Our results on real-world attack data demonstrates that the proposed method has exceptional performance with 97.33 % detection accuracy and 0% false alarm rate, which significantly outperform the state-of-the-art. Furthermore, attack classification achieves 82.33 % accuracy for spoofing and 94.31 % for jamming attacks, with an overall F1 score of 0.88.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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".