Automated Spam Call Traceback: Two Efficiency Enhancement Approaches
Bibliographic record
Abstract
Spam calls have been a persistent issue, leading to significant economic and social harm. Spam call traceback is a crucial measure to combat spam calls by identifying fraudsters and holding problematic providers accountable. An automated spam call traceback method, i.e., Jager, was proposed to address low efficiency issues of manual traceback. However, apart from complex cryptographic operations, it requires traceback authority (TA) to generate a call label for every call, and all the call detail records (CDRs) are required to be stored at a central server. These generates very high and unnecessary traffic and computation loads. In this paper, we first investigate a simple automated spam call traceback method, namely distributed CDR sharing (DCS).With this method the carriers grant access of their local CDRs to an automated call traceback center (ACTC). The ACTC only accesses the CDRs for reported spam calls via secure APIs. The call path can be automatically reconstructed to locate the spam call origins. As non-cooperative carriers (such as legacy and malicious carriers) may break the traceback automation, we propose an enhanced automated spam call tracing (ASCT) method to address the issue. ASCT uses locally stored chained CDR blocks for mutual verification between carriers. Only when non-cooperative carriers are encountered, copies of CDRs are send to a central CDR server to help mitigate the impact of the non-cooperative carriers. The proposed methods are evaluated and compared to the manual and Jager methods. Experiment results show that the proposed methods are very efficient and scalable, while achieving a similar level of security performance to that of the manual method. Under the condition of all cooperative carriers, full call tracing automation can be achieved without generating any traffic to the central CDR server.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".