FL-BC-IDS: Evidence-Native Privacy-Aware Hierarchical Federated Intrusion Detection for the Internet of Vehicles
Sensors, cilt.26, sa.17, 2026 (SCI-Expanded, Scopus)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 26 Sayı: 17
- Basım Tarihi: 2026
- Doi Numarası: 10.3390/s26175400
- Dergi Adı: Sensors
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Compendex, EMBASE, INSPEC, MEDLINE, Directory of Open Access Journals, Academic Search Ultimate (EBSCO), Biomedical Reference Collection: Corporate Edition (EBSCO), Health Research Premium Collection (ProQuest)
- Anahtar Kelimeler: blockchain, differential privacy, federated learning, Internet of Vehicles, intrusion detection, verifiable evidence
- Yıldız Teknik Üniversitesi Adresli: Evet
Özet
Internet of Vehicles (IoV) intrusion detection systems (IDSs) require collaborative learning that preserves raw-data locality while producing independently checkable post-run evidence. This paper presents FL-BC-IDS, an evidence-native, privacy-aware hierarchical federated IDS in which vehicles train Differentially Private XGBoost models, roadside units perform deterministic admission and tree-bagging aggregation, and the GLOBAL stage forms an equal-weight ensemble over validated RSU models. Signed reports, privacy records, SHA-256/Poseidon commitments, scoped Groth16 proofs, reconstructable public inputs, and digest-pinned blockchain receipts provide a unified verification path. Across 10 seed-controlled runs, the mean ± SD accuracy/F1 values were (Formula presented.) / (Formula presented.) on CSE-CIC-IDS2018 and (Formula presented.) / (Formula presented.) on CICIoV2024. With thresholds fixed exclusively from development data, the strict held-out-attack macro recall was 0.8031 and 0.9090 on CSE-CIC-IDS2018 and CICIoV2024, respectively, indicating residual attack-specific generalization limitations; supervised rolling-origin temporal refresh on CSE-CIC-IDS2018 achieved 0.984788 pooled seen-attack recall at a 0.005700 test FPR. A controlled 20-vehicle, eight-round heterogeneity and participation stress test retained 0.998151 accuracy and 0.984782 F1-score. Verification rejected invalid or context-mismatched artifacts and independently checked model–anchor consistency, RSU aggregation replay, commitments, and public inputs. The reported DP budgets are conditional learner-stage bounds for learner-input record instances, not end-to-end guarantees for original pre-preprocessing records.