Closed-Loop DDoS Mitigation System in Software Defined Networks
Bibliographic record
Abstract
In Software Defined Networking (SDN) with the centralized controller structure, Distributed Denial of Service (DDoS) attacks can exhaust the controller's or the nodes' computing and communication resources; thus, breakdown of the network could happen. Threat vectors for DDoS attack can be the main components of SDN, such as the control plane, the data plane, and/or the application plane. This paper focuses on protecting servers in the SDN networks from DDoS attacks. We focus specifically on protocol attacks. This type of attack consumes target server resources, or the communication resources allocated for the target server. Using a feedback loop from the data plane to the control plane in real-time, we can anticipate future attacks and control the attack reactively. Processing all the traffic going through an SDN network at the control plane in real-time can overwhelm the controller. To prevent this a Network Function Virtualization (NFV) node can be configured in the SDN where the traffic processing can take place. Hence a closed-loop system where the real-time traffic is monitored from a NFV in the SDN that reports to the controller in the SDN can mitigate DDoS attacks. The NFV can monitor the real-time network traffic for any upsurges in a pre-defined traffic flow that crosses a pre-configured threshold. The threshold can be chosen based on information from previous attacks. In the event of an attack the NFV can report to the controller which can in turn take appropriate action. In this paper, we propose two closed-loop methods to protect servers in SDN from DDoS attacks. The objective of this paper is to protect the host machines in SDN from DDoS attacks that originate from within the network itself. We implemented the proposed methods and compared the two methods for further analysis. Our closed-loop systems can mitigate the DDoS attacks in real-time. The rate at which the attacks were mitigated was largely influenced by the value of the threshold that is configured.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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 teacher head, 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".