Detection and Classification of Darknet Traffic Using an Enhanced LocalKNN Algorithm
Bibliographic record
Abstract
Using the dark web is inevitable due to the wide range of anonymous services that are provided, which can be accessed via the Onion Router (TOR) and Virtual Private Network (VPN).Anonymity creates an environment where malicious activities occur out of reach of law enforcement.Such activities have huge implications for society's safety and organizations' cybersecurity environment.Therefore, this paper tackled these challenges by proposing a darknet traffic detection and categorization model that can flag users who can access the darknet.The proposed model utilizes different techniques in machine learning, starting from pre-processing (data cleaning, encoding, and balancing) that prepares data before selecting the top 50 best features, using Chi-Square, which can then be used to train a classifier model built based on local K-Nearest Neighbors (KNN) and City and Hamming as distance metrics.The improved K-Nearest Neighbors with Local Metric Induction (LocalKNN) algorithm calculates a local metric as an additional step for each classified object.During the process of classifying test objects, classifiers use global metrics to find a large set of nearest neighbors, which is then used to derive a new local metric set.Finally, a locally induced metric is used to select the nearest neighbors.The model shows a great potential result in detecting traffic with an accuracy of 99.34% and a categorization accuracy of 92.34%.
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 | 0.002 |
| 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 | 0.001 |
| 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".