Privacy-Preserving Intrusion Detection Using Federated Learning and Differential-Privacy-Inspired Noise
Bibliographic record
Abstract
Artificial Intelligence (AI) has strengthened the effectiveness of Intrusion Detection Systems (IDS), but their reliance on metadata such as IP addresses, traffic patterns, and timestamps introduces notable privacy risks. While these features improve detection accuracy, they may also reveal sensitive behavioural information that can support profiling or inference attacks. This paper investigates a lightweight privacy-preserving IDS framework that integrates Federated Learning (FL) with a noisebased perturbation mechanism inspired by differential privacy (DP). Using Random Forest (RF) and Support Vector Machine (SVM) classifiers, we evaluate four configurations-RF + FL, $\mathbf{R F} \boldsymbol{+} \mathbf{F L} \boldsymbol{+} \mathbf{D P}$-inspired noise, $\mathbf{S V M} \boldsymbol{+} \mathbf{F L}$, and SVM + FL + DP-inspired noise-on the CIC-IDS2017 dataset. The noise mechanism follows DP intuition but does not claim formal ($\varepsilon, \delta$) guarantees. Among all configurations, $\mathbf{R F} \boldsymbol{+} \mathbf{F L}$ provides the strongest performance, achieving 92% accuracy with a false positive rate of 0.09. Injecting noise reduces accuracy but enhances empirical protection of metadata. The findings show that combining FL with calibrated noise can support effective intrusion detection while offering a practical and measurable privacy-utility balance for sensitive environments.
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 | 0.005 | 0.015 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| 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".