A Time-Series and Density-Based Filter for DNS Log Reduction and Analysis
Bibliographic record
Abstract
The Domain Name Service (DNS) is fundamental to the successful operation of the Internet, providing behind the scenes translation between Uniform Resource Locators (URLs) used by humans and machines and the Internet Protocol (IP) addresses required for data transmission between hosts and servers. DNS is ubiquitous across networks and for decades has been used for malicious purposes by threat actors. There has been significant research in detecting DNS protocol abuse leveraging statistical analysis, natural language processing and machine learning. The volume of DNS traffic in enterprise networks is significant and leveraging detection techniques on large datasets is costly in terms of time, processing and memory resources. There is a need to reduce the size of DNS logs to enable more efficient use of detection techniques and reduce the amount of data to be reviewed by analysts. The aim of this research was to develop and evaluate a log filtering technique to reduce DNS log size while retaining sufficient malicious traffic samples to enable efficient analysis and DNS abuse detection. This technique leverages a single time-delta feature and density-based clustering to reduce DNS log size. The results showed up to a 76% decrease in log size by row count and up to 99 % reduction in user IP and DNS query pairs while retaining up to 83% of malicious traffic. Operationally, this provides a much reduced dataset size for analysts that requires less time and computational resources to process.
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 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.001 | 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) | 0.002 | 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".