Performance Analysis of Regex-Based Processing for Dark Web Targeted Crawling
Bibliographic record
Abstract
Data crawling in the dark web holds a critical significance in bolstering security intelligence efforts.Previous research has successfully developed fast crawlers for specific purposes such as digital investigations, abusive content, automated captcha breaking, etc.However, this research mostly focuses on faster download time and has not paid attention to the importance of assessing crawl accuracy.Due to the fast-changing dark web shape and content, accurate and complete crawled data is a vital part of security intelligence.This research has successfully developed a targeted dark web crawler by combining the focus and in-depth crawling for The Onion Router (TOR) network.Regex Text, Regex Wildcard, and Regex Optional are used to automatically filter the content by a specific keyword.The effectiveness of the crawler was tested in the five real-world dark website environments.From the testing with a depth of 3, the application achieved more than 98% accuracy.The Regex Optional processing performance was faster than the Regex Text and Regex Wildcard by over a second, due to the swift crawling attempt.In terms of accuracy, the Regex Optional achieved 99.14% which is 4.83% higher than Regex Text.The best keyword processing method in targeted crawling is Regex Optional, with an accuracy rate of over 99%.
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 | 0.003 | 0.016 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.002 |
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".