Edge Intelligence Enabled Soft Decentralized Authentication in UAV Swarm
Bibliographic record
Abstract
With the increased deployment of the Unmanned Aerial Vehicles (UAVs) in both military and civilian fields, the authentication of the UAV surveillance and controlling data becomes critical due to the severe consequences of any forged data. With the highly dynamic operation environment, a flying UAV network may not be supported by the infrastructure network on the ground for security provision. Hence, it is vital to improving network security by utilizing on-site resources within a flying UAV swarm. In this paper, we utilize the physical-layer fingerprints to increase the difficulty for the attackers to impersonate the legitimate UAVs. A decentralized authentication scheme is proposed to avoid the single-point failure at the cluster head (CH) caused by the imperfect estimations. To mitigate the high computational cost of the decentralized authentication and to further improving the authentication accuracy, a situational-aware authentication customization algorithm is proposed at each UAV to compute the reliability of different attributes. Only the UAV with reliable attributes observations will contribute to the decentralized authentication process. Moreover, a soft authentication decision algorithm, which is compatible with customized regression models at each UAV, is proposed to further improve the system robustness. Hence, the proposed authentication algorithm can be customized at the system level and node level to maximize the overall authentication accuracy under a minimal extra computational cost based on the decentralized process. The simulation results demonstrate that our proposed scheme significantly increased the accuracy by comparing to the other state-of-the-art machine learning-aided physical-layer authentication schemes.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".