Adaptive Clustering Approaches for Domain Name System Anomaly Detection: Comparative Performance Analysis
Bibliographic record
Abstract
The Domain Name System (DNS) is exploited for sophisticated threats like botnet control, evading signature-based detection.This study evaluates four unsupervised clustering algorithms: K-means, DBSCAN, Hierarchical Clustering, and Gaussian Mixture Models (GMM), on 100,001 DNS queries with 84 features.Parameters were optimized via GridSearchCV, with comparisons across raw data, principal component analysis (PCA), and t-distributed Stochastic Neighbor Embedding (t-SNE).Results show dimensionality reduction is critical: raw data yielded poor separation (Davies-Bouldin Index (DB Index) up to 2.94), while t-SNE enabled DBSCAN to achieve the best cluster separation (DB Index = 1.29).K-means and Hierarchical Clustering showed strong agreement (96% similarity on PCA data), whereas GMM effectively modeled overlapping stealthy attack behaviors.Cross-algorithm similarity varied dramatically (K-means vs. GMM: 14-28%), highlighting that consensus depends heavily on data representation.These findings demonstrate performance is highly representation-dependent, providing empirical support for hybrid DNS security systems that select algorithms based on threat characteristics and preprocessing strategy.Real-time deployment faces computational constraints, motivating future work in optimized implementations.
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 | 0.005 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".