DeltaShield: Information Theory for Human- Trafficking Detection
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Given a million escort advertisements, how can we spot near-duplicates? Such micro-clusters of ads are usually signals of human trafficking (HT). How can we summarize them to convince law enforcement to act? Spotting micro-clusters of near-duplicate documents is useful in multiple, additional settings, including spam-bot detection in Twitter ads, plagiarism, and more. We present InfoShield , which makes the following contributions: practical , being scalable and effective on real data; parameter-free and principled , requiring no user-defined parameters; interpretable , finding a document to be the cluster representative, highlighting all the common phrases, and automatically detecting “slots” (i.e., phrases that differ in every document); and generalizable , beating or matching domain-specific methods in Twitter bot detection and HT detection, respectively, as well as being language independent. Interpretability is particularly important for the anti-HT domain, where law enforcement must visually inspect ads. Our experiments on real data show that InfoShield correctly identifies Twitter bots with an F1 score over 90% and detects HT ads with 84% precision. Moreover, it is scalable, requiring about 8 hours for 4 million documents on a stock laptop. Our incremental version, DeltaShield , allows for fast, incremental updates, with minor loss of accuracy.
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.
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 | 0.001 | 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 | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.007 |
| Open science | 0.002 | 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 it