Preventing SIM Box Fraud Using Device Model Fingerprinting
Bibliographic record
Abstract
SIM boxes have been playing a critical role in the underground ecosystem of international-scale frauds that steal billions of dollars from individual victims and mobile network operators across the globe.Many mitigation schemes have been proposed for these frauds, mainly aiming to detect fraud call sessions; however, one direct approach to this problem-the prevention of the SIM box devices from network use-has not drawn much attention despite its highly anticipated benefit.This is exactly what we aim to achieve in this paper.We propose a simple access control logic that detects when unauthorized SIM boxes use cellular networks for communication.At the heart of our defense proposal is the precise fingerprinting of device models (e.g., distinguishing an iPhone 13 from any other smartphone models on the market) and device types (i.e., smartphones and IoT devices) without relying on international mobile equipment identity, which can be spoofed easily.We empirically show that fingerprints, which were constructed from network-layer auxiliary information with more than 31K features, are mostly distinct among 85 smartphones and thus can be used to prevent the vast majority of illegal SIM boxes from making unauthorized voice calls.Our proposal, as the very first practical, reliable unauthorized cellular device model detection scheme, greatly simplifies the mitigation against SIM box frauds.
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 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.003 |
| Open science | 0.001 | 0.002 |
| 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".