ZTID-IoV: Zero-Trust Intrusion Detection in IoV Using Neurosymbolic AI Approach With Federated Meta-Learning
Bibliographic record
Abstract
The rapid growth of the Internet of Vehicles (IoVs) and smart consumer electronics has generated cybersecurity concerns that require an intelligent, adaptable, and privacy-preserving Intrusion Detection System (IDS). This study introduces ZTID-IoV, a novel neurosymbolic AI framework that integrates federated learning, lightweight transformers, and meta-learning to improve threat detection while preserving user privacy in consumer IoVs. Our approach leverages neural components such as a transformer model for recognizing patterns in network traffic, combined with symbolic AI techniques such as self-organizing maps for interpretable client clustering and rule-guided reasoning, to achieve robust cybersecurity in distributed environments. A lightweight transformer architecture optimizes performance for resource-constrained edge devices, and SOM-based clustering enhances model aggregation by grouping devices with similar behavioral patterns. The proposed system employs Model-Agnostic Meta-Learning (MAML) to enable rapid adaptation to emerging threats across diverse consumer devices, while federated learning ensures decentralized model training without exposing sensitive user data. Experiments on real-world IoT intrusion datasets demonstrate that our framework achieves higher detection accuracy compared to centralized and pure neural approaches while maintaining low computational overhead. Additionally, the neurosymbolic design provides interpretable threat explanations, crucial for consumer applications where transparency is essential. The results highlight the potential of ZTID-IoV in enabling zero-trust security for IoV and other connected consumer electronics. This work contributes to the evolving landscape of AI-driven cybersecurity by addressing critical challenges in privacy and adaptability, making ZTID-IoV particularly suitable for next-generation IoV ecosystems.
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 | 0.003 |
| 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 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.002 |
| 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".