The Secret Sharer¶
Carlini, N., Liu, & Erlingsson. (2019). The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks. 28th USENIX Security Symposium (USENIX Security 19), 267-284.
Cited by¶
1 citation across 1 artifact.
Each citation links to the sentence it supports in the citing article.
Mechanisms¶
- Model Inversion Red Team
- Its strength is that it is the only test here that treats the trained model, not a table, as the leak, catching the memorisation and inversion that data-level redaction leaves untouched; canaries turn "we couldn't extract anything" into a measured rate rather than a hope
This sourceIntroduces canaries and an exposure metric for quantitatively testing unintended memorization in trained models.
- Its strength is that it is the only test here that treats the trained model, not a table, as the leak, catching the memorisation and inversion that data-level redaction leaves untouched; canaries turn "we couldn't extract anything" into a measured rate rather than a hope
Verification¶
Does it exist? Not checked yet. This entry carries no identifier to resolve. It was extracted from the citation as written in the article, normalized, and deduplicated against the rest of the registry.
Does it back the claim? Not recorded. The single citation of this work carries no recorded support check.
Was it audited? Yes. A second, independent pass read the citation against the article text and recorded a verdict.
Support is checked per citation rather than per work — the same source can be cited soundly in one article and wrongly in another. Per-citation recording began recently, so a citation with no recorded check is a gap in the record rather than evidence it went unchecked.
See how references were verified.
Registry ID ref:98bd8f7ad448 · see in the full table