Privacy leakage in multi-relational learning via unwanted classification models
Bibliographic record
Abstract
Multirelational classification algorithms aim to discover patterns across multiple interlinked tables in a relational database. However, when considering a complex database schema, it becomes difficult to identify all possible relationships between attributes. This is because a database often contains a very large number of attributes which come from different interconnected tables with non-determinate (such as one-to-many) relationships. A set of seemingly harmless attributes across multiple tables, therefore, may be used to learn unwanted classification models to accurately determine confidential information, leading to data leaks. Furthermore, eliminating or distorting confidential attributes may be insufficient to prevent such data disclosure, since values may be inferred based on prior insider knowledge. This paper proposes an approach to identify such "dangerous" attribute sets. For data publishing, our method generates a ranked list of subschemas which maintain the predictive performance on the class attribute, while limiting the disclosure risk, and predictive accuracy, of confidential attributes. We demonstrate the effectiveness of our method against several databases.
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 | 0.020 | 0.061 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.002 | 0.004 |
| Science and technology studies | 0.002 | 0.003 |
| Scholarly communication | 0.005 | 0.009 |
| Open science | 0.003 | 0.005 |
| Research integrity | 0.002 | 0.004 |
| 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".