NEMESIS: An Enhanced Hybrid Intrusion Detection System Leveraging Deep Q-Learning and Random Forest
Bibliographic record
Abstract
Network intrusion detection systems (NIDS) face the growing difficulty posed by increasingly sophisticated and unseen attacks, which represent a dangerous threat due to their ability to exploit vulnerabilities that have not yet been identified. These attacks are inherently difficult to detect with conventional NIDS because such systems typically are built on known threat patterns or signatures, which are absent in unseen scenarios. Consequently, this greatly limits their efficacy in mitigating advanced threats, making networks susceptible to potential security breaches. To address these challenges, recent years have witnessed the emergence of various Reinforcement Learning (RL) approaches aimed at enhancing the automatic detection of network intrusions. These systems are equipped with autonomous agents that acquire the ability to learn independently and make decisions without requiring direct input or knowledge of human experts. In this paper, we propose a network intrusion detection mechanism that integrates a Deep Q Network-based model (DQN) with a supervised machine learning algorithm specifically designed for attack classification. Our model is characterized by meticulous fine-tuning of hyperparameters to optimize the performance of detection. Extensive experimental evaluations that take advantage of the NSL-KDD and CSE-CICIDS2017 datasets demonstrate that our hybrid approach significantly improves detection accuracy across various types of attack and outperforms other existing state-of-the-art solutions designed for similar purposes.
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 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".