Deep Reinforcement Learning-Based Intrusion Detection System for Next-Generation Wireless Networks
Bibliographic record
Abstract
Of late, this is due to fast evolution of next generation wireless networks, such as 5G, and unprecedented growth in number of connected devices and heterogeneous network architectures. This proliferation greatly increases the surface area for potential cyber threats and conventional Intrusion Detection Systems (IDS) are not sufficient because they are static and signature based. In this paper, we present a novel IDS based on Deep Reinforcement Learning used on dynamic and complex wireless environments. The system uses the adaptive learning capability of DRL to obtain optimal defense strategies by having continuous interaction with the network environment, and having the attack patterns evolve. The proposed model is based on a Dueling Deep Q Network (Dueling-DQN) architecture fortified with the use of prioritized experience replay for this purposes. Experimental evaluations on benchmark wireless traffic datasets show that our DRL-IDS achieves much better performance in detecting known as well as zero day attacks to a level very close to the lower bound set by the ideal detector while containing minimal false positives. In addition, the system is able to adapt to real time, scale up and robust, which makes it a perfect solution for securing the future wireless communication infrastructures (e.g. smart cities, vehicular networks and IoT driven ecosystem).
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 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) | 0.001 | 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".