Lightweight IDS For UAV Networks: A Periodic Deep Reinforcement Learning-based Approach
Bibliographic record
Abstract
The use of intrusion detection systems (IDS) has become crucial for modern networks. To ensure the targeted performance of such networks, diverse techniques were introduced to enhance system reliability. Many network designs have adapted the use of Unmanned Aerial Vehicles (UAVs) to provide wider coverage and meet performance targets. However, the cybersecurity aspect of UAVs has not been fully considered. In this paper, we propose a lightweight intrusion detection and prevention system (IDPS) module for UAVs. The IDPS module is trained using Deep Reinforcement Learning (DRL), specifically Deep Q-learning (DQN), to enable UAVs to autonomously detect suspicious activities and to take necessary action to ensure the security of the network. A customized reward function is used to take into consideration the dataset unbalanced nature, which encourages the IDPS module to detect minor classes. Also, considering the limited availability of resources for UAVs, a periodic offline-learning approach is introduced to ensure that UAVs are capable to learn and adapt to the evolution of intrusion attacks autonomously. Numerical simulations show the efficiency of the proposed IDPS in detecting suspicious activities and corroborating the advantages brought by the periodic offline learning in comparison with similar online learning approaches, in terms of accuracy and energy consumption.
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 | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".