Machine Learning Approach to False Alert Attack Detection in Vehicular Adhoc Networks
Bibliographic record
Abstract
The expansion of Intelligent Transportation Systems (ITS) and their integration into Vehicular Adhoc Networks (VANETs) bring a number of critical safety and security concerns. Among many is the false reporting attack, in which a malicious actor sends adversarial messages to fabricate artificial traffic incidents. To ensure safety and reliability, addressing false alert attacks is particularly crucial due to the potential danger that this type of attack poses. False alerts may cause vehicles to take unnecessary evasive maneuvers to avoid non-existent hazards, which might lead to accidents and endanger the safety of drivers, passengers, and other road users. In this research, we aim to address this threat of false alert attacks in VANETs by using the VeReMiAP Dataset (a VeReMi-based dataset) as a benchmark and develop machine learning (ML) models and approaches to detect and mitigate false alert attacks in VANETs. The methodology includes a detailed analysis of the dataset, feature engineering in conjunction with plausibility, and the use of state-of-the-art ML models for detection. The research findings show that the proposed approach can effectively detect false alert attacks in VANETs. The results show that this approach is effective for detecting the attack with high accuracy and F1 score. The research also provides insights into the performance of different ML models and the importance of feature engineering in detecting false alert attacks. The research findings can be used to develop more robust and reliable security mechanisms to ensure the safety and security of road users.
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 | 0.002 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.000 | 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".