Utility of Knowledge Discovered from Sanitized Data
Bibliographic record
Abstract
While much attention has been paid to data sanitization methods with the aim of protecting users’ privacy, far less emphasis has been put to the usefulness of the sanitized data from the view point of knowledge discovery systems. We consider this question and ask whether sanitized data can be used to obtain knowledge that is not defined at the time of the sanitization. We propose a utility function for knowledge discovery algorithms, which quantifies the value of the knowledge from a perspective of users of the knowledge. We then use this utility function to evaluate the usefulness of the extracted knowledge when knowledge building is performed over the original data, and compare it to the case when knowledge building is performed over the sanitized data. Our experiments use an existing cooperative learning model of knowledge discovery and medical data, anonymized and perturbed using two widely known sanitization techniques, called E-differential privacy and k-anonymity. Our experimental results show that although the utility of sanitized data can be drastically reduced and in some cases completely lost, there are cases where the utility can be preserved. This confirms our strategy to look at triples consisting of a utility function, a sanitization mechanism, and a knowledge discovery algorithm that are useful in practice. We categorize a few instances of such triples based on usefulness obtained from experiments over a single database of medical records. We discuss our results and show directions for future work.
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 | 0.025 | 0.109 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.004 |
| Science and technology studies | 0.001 | 0.003 |
| Scholarly communication | 0.005 | 0.008 |
| Open science | 0.001 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".