Identifying Spurious Hash Addresses in the Bitcoin Network and Making Predictions Using Various ML Models
Bibliographic record
Abstract
Bitcoin is a cryptocurrency that operates on the principles of blockchain technology, which means that it allows transferring funds from one node to another without intermediaries such as banks. It eliminates the necessity of central authority and ensures secure and transparent transactions using hash addresses. Bitcoin's popularity stems from its ability to facilitate online transactions and digital currency transfers. However, the open nature of a Bitcoin network and the use of hash keys for transactions makes it vulnerable to hacking attempts, leading to billions of dollars in cryptocurrency losses annually. In our research, we build a Bitcoin transaction network using blockchain graph features from a Regular dataset (including real and fake hash addresses) to analyze the percentage of fake addresses within the darknet market (Grams dataset) using timestamp values. Through this analysis, we aim to gain insights into the prevalence of fraudulent addresses within the darknet market. We consider transaction time (timestamp) as it will be the same for both datasets. For the first time, we have used machine learning models for predicting fake addresses. In our experiment, we have utilized two machine-learning models: Random Forest and XG Boost classifier, and have found that 77.86% of total addresses from darknet markets are fake, and Random Forest shows higher accuracy than XG Boost for predicting fake addresses.
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 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| 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 | 0.001 |
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".