Attack Endgame: Proactive Security Approach for Predicting Attack Consequences in VANET
Bibliographic record
Abstract
In the fast dynamic environment of Vehicle Ad Hoc Networks (VANETs), proactive security measures are necessary. Reactive security has been VAVNETs' guardian angel for some time, but now it is insufficient against current security attacks. Attack prediction is a promising solution capable of keeping up with the recent cyber security challenges. First, we need to understand where prediction fits in the attack process. To accomplish this, we introduce an attack life cycle in a VANET and exploit the proactive and retroactive phases. One of the proactive phases is the after-effect of the attack or what we call attack endgame. We use the Framework for Misbehavior Detection (F2MD) to simulate an attack effect with adverse side effects on road traffic. We implement traffic warning messages in F2MD. Then, we create attacks on these messages, namely “fake accident”, and simulate the effect of these attacks on the vehicles while capturing the results using F2MD. We simulate the impact of acting on these messages or the attack endgame, which manifested in creating hazards. We use Recurrent Neural Network (RNN) models to predict the endgame of the fake accident attack on the road. We experiment with vanilla artificial neural network solutions to create a baseline. Afterward, we use Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU) to build a stacked RNN model to predict the attack endgame at different time windows. They effectively predict the occurrence of a hazard up to 3.5 minutes ahead with over 80% accuracy.
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 | 0.001 |
| 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 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| 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".