In-Network Defense: Safeguarding the Network Against Evolving DDoS Attacks
Bibliographic record
Abstract
Emerging technologies that encompass a multitude of tiny wearable devices are vulnerable to cyberattacks that can turn them into bots for launching Distributed Denial of Service (DDoS) attacks. In-network Machine Learning (ML) has emerged as a prominent solution for detecting and responding to such attacks in the shortest possible time to avoid disrupting user experience. However, the dynamic nature of attack traffic patterns necessitates continuous adaptation of conventional one-size-fits-all ML models. The manual process of identifying novel malicious traffic patterns and updating the ML model from the control plane to the network data plane is time-consuming and labor-intensive. This study aims to automate the identification of unseen malicious traffic patterns and update the ML model in programmable networks using a data-driven approach. Specifically, we determine drift detection thresholds from the baseline performance of historical (i.e., training) data and consider any deviation as anomalies in unseen (i.e., testing) data. These thresholds are continuously updated by considering changes in the data distribution and in-network inference results. We utilize an intrusion detection dataset (CIC-IDS2017) to illustrate the impact of emerging attacks on model performance degradation and the efficacy of our proposed data-driven method in mitigating these attacks. Our approach has proven effective in safeguarding against evolving DDoS attacks.
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 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| 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".