DDoS Detection System: Using a Set of Classification Algorithms Controlled by Fuzzy Logic System in Apache Spark
Bibliographic record
Abstract
Distributed denial of service (DDoS) attacks are a major security threat against the availability of conventional or cloud computing resources. Numerous DDoS attacks, which have been launched against various organizations in the last decade, have had a direct impact on both vendors and users. Many researchers have attempted to tackle the security threat of DDoS attacks by combining classification algorithms with distributed computing. However, their solutions are static in terms of the classification algorithms used. In fact, current DDoS attacks have become so dynamic and sophisticated that they are able to pass the detection system thereby making it difficult for static solutions to detect. In this paper, we propose a dynamic DDoS attack detection system based on three main components: 1) classification algorithms; 2) a distributed system; and 3) a fuzzy logic system. Our framework uses fuzzy logic to dynamically select an algorithm from a set of prepared classification algorithms that detect different DDoS patterns. Out of the many candidate classification algorithms, we use Naive Bayes, Decision Tree (Entropy), Decision Tree (Gini), and Random Forest as candidate algorithms. We have evaluated the performance of classification algorithms and their delays and validated the fuzzy logic system. We have also evaluated the effectiveness of the distributed system and its impact on the classification algorithms delay. The results show that there is a trade-off between the utilized classification algorithms' accuracies and their delays. We observe that the fuzzy logic system can effectively select the right classification algorithm based on the traffic status.
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) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".