Detecting IPv6 SEND Flooding Attacks Using a Machine Learning Framework
Bibliographic record
Abstract
The transition to IPv6 introduces new security challenges, particularly within the Neighbor Discovery Protocol (NDP). While the SEcure Neighbor Discovery (SEND) protocol was designed to protect NDP using cryptographic mechanisms, its reliance on computationally expensive signature verification creates a vulnerability to resource-exhaustion attacks. This paper addresses the sophisticated threat of the SEND flooding attack, where an adversary can induce a Denial of Service by overwhelming a target node's CPU with valid-looking, signed packets. Traditional detection methods struggle against such attacks, which do not rely on malformed packets. To counter this threat, we propose a multi-stage machine learning framework designed to distinguish between legitimate and malicious SEND traffic. We conducted a comparative analysis of five machine learning algorithms, leveraging advanced feature engineering to create a rich set of statistical and content-based features. The results demonstrate that the Gradient Boosting model achieved superior performance, with Accuracy and F1-score of 91.24% and 91.48% respectively, effectively identifying the attack with high precision and recall. This research validates that a data-driven, behavioral analysis approach can successfully defend against complex, protocol-level resource-exhaustion attacks, providing a critical security layer for modern IPv6 networks.
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 | 0.003 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".