HyFIDS: Hybrid Frequency-Aware Lightweight Intrusion Detection for Internet of Vehicles
Bibliographic record
Abstract
Intrusion Detection Systems (IDSs) play a crucial role in the Internet of Vehicles (IoV) by safeguarding against reliability and security threats arising from the growing complexity and interconnectivity. However, existing deep learning (DL)-based IDSs, particularly those relying on resource-intensive architectures, often fail to meet the limited computational resource constraints of IoV gateways and tend to overlook real-world deployment considerations. To address these challenges, we propose HyFIDS, a hybrid frequency-aware lightweight intrusion detection system, for IoV ecosystems. HyFIDS integrates raw packet representations with frequency-domain representations through a novel frequency-aware module. This design enables HyFIDS to extract temporal and spectral features of both CAN frames and IP packets, thereby enhancing representational efficiency while maintaining computational lightweightness. To validate its performance, we implement HyFIDS on four benchmark datasets encompassing both inter-vehicle and intra-vehicle scenarios. Extensive experiments demonstrate that HyFIDS achieves a high detection accuracy of 99.98%, maintains a lightweight model with only 20K MACs, and obtains the highest throughput of 8.9 Mbps.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".