Gradient Monitored Reinforcement Learning for Jamming Attack Detection in FANETs
Bibliographic record
Abstract
Unmanned Aerial Vehicles (UAVs) have several military and civilian applications to perform tasks that do not require a central processing unit or human involvement. There are several vulnerable characteristics, alternatively limitations, in UAV systems such as data loss, signals interference, disabling sensors, misleading weapons, cyber attacks, disrupting services, etc. Jamming attack is one of the cyber threats that likely lead to denial of service that often occurs in wireless communication systems like Flying ad hoc networks (FANETs) and Internet of Drones (IoD). Over years, there are several approaches proposed by researchers to detect jamming attacks such as rule-based jamming attack detection mechanism, Bayesian game-theoretic mechanism, IoD-based protection mechanism, communication channel techniques (channel hopping, spectrum spreading, MIMO-based jamming mitigation, coding, etc), delay tolerant networking technique, and cryptographic algorithms, however, these methods were not suitable for jamming detection in UAV environment. The major challenges are on the delivery efficiency, processing time, accuracy, energy consumption, flight distance, and flight autonomy. In this paper, we introduce a method to detect the Jamming Attack using Reinforcement Learning-based Gradient Monitored (RLGM) mechanism. RLGM maintains safe regions and reduces gradient variance for intended training and this provides a better accuracy of the learning goal. In addition, RLGM achieves prompt training progress and selects preciously the series of parameters required by the network during the training phase. RLGM produces spontaneous derivation of the essential deep network scale over the training process drawing on automatically unvarying trained weights. Our proposed approach outperforms other reinforcement learning methods such as Federated RL, Deep Q Learning (DQL), and GA-AOMDV.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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 teacher head, 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".