# Privacy-utility tradeoff on FIQA Source: [Privacy-utility tradeoff on FIQA]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:48:33.862Z Evaluation of the tradeoff between data leakage and model utility when using the FIQA dataset, measured by Leakage, Confidence, and Downstream performance. A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. | Scope | Recorded value | | --- | --- | | Task | Privacy-utility tradeoff | | Dataset (including any stated split) | FIQA | | Metric | Leakage | | Unit | PERCENT | | Direction | Lower is better | | Results loaded | 16 of 16 | | Coverage | All results currently returned for this benchmark | Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol. ## Metrics - [Leakage](): Lower is better; unit: PERCENT. - [Confidence](): Higher is better; unit: SCALAR. - [Downstream Performance](): Higher is better; unit: SCALAR. ## Recorded results | Method | Leakage | Result date | Report paper | | --- | --- | --- | --- | | SPARSE | 8.48 | Not recorded | 698abbaec97a0b3e3b5de035 | | LapMech | 12.56 | Not recorded | 698abbaec97a0b3e3b5de035 | | PurMech | 13.01 | Not recorded | 698abbaec97a0b3e3b5de035 | | SPARSE | 31.62 | Not recorded | 698abbaec97a0b3e3b5de035 | | LapMech | 35.17 | Not recorded | 698abbaec97a0b3e3b5de035 | | PurMech | 35.31 | Not recorded | 698abbaec97a0b3e3b5de035 | | SPARSE | 53.41 | Not recorded | 698abbaec97a0b3e3b5de035 | | PurMech | 55.38 | Not recorded | 698abbaec97a0b3e3b5de035 | | LapMech | 55.69 | Not recorded | 698abbaec97a0b3e3b5de035 | | SPARSE | 63.51 | Not recorded | 698abbaec97a0b3e3b5de035 | | LapMech | 64.12 | Not recorded | 698abbaec97a0b3e3b5de035 | | PurMech | 64.13 | Not recorded | 698abbaec97a0b3e3b5de035 | | SPARSE | 68.13 | Not recorded | 698abbaec97a0b3e3b5de035 | | PurMech | 68.63 | Not recorded | 698abbaec97a0b3e3b5de035 | | LapMech | 68.85 | Not recorded | 698abbaec97a0b3e3b5de035 | | Unprotected embedding | 77.35 | Not recorded | 698abbaec97a0b3e3b5de035 | ### SPARSE Leakage: 8.48. Result ID: 6996dcfd5698665ec4297139. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"5"}. This record does not assert independent reproduction. ### LapMech Leakage: 12.56. Result ID: 6996dcfd5698665ec4297137. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"5"}. This record does not assert independent reproduction. ### PurMech Leakage: 13.01. Result ID: 6996dcfd5698665ec4297138. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"5"}. This record does not assert independent reproduction. ### SPARSE Leakage: 31.62. Result ID: 6996dcfd5698665ec429713c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"10"}. This record does not assert independent reproduction. ### LapMech Leakage: 35.17. Result ID: 6996dcfd5698665ec429713a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"10"}. This record does not assert independent reproduction. ### PurMech Leakage: 35.31. Result ID: 6996dcfd5698665ec429713b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"10"}. This record does not assert independent reproduction. ### SPARSE Leakage: 53.41. Result ID: 6996dcfd5698665ec429713f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"20"}. This record does not assert independent reproduction. ### PurMech Leakage: 55.38. Result ID: 6996dcfd5698665ec429713e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"20"}. This record does not assert independent reproduction. ### LapMech Leakage: 55.69. Result ID: 6996dcfd5698665ec429713d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"20"}. This record does not assert independent reproduction. ### SPARSE Leakage: 63.51. Result ID: 6996dcfd5698665ec4297142. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"30"}. This record does not assert independent reproduction. ### LapMech Leakage: 64.12. Result ID: 6996dcfd5698665ec4297140. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"30"}. This record does not assert independent reproduction. ### PurMech Leakage: 64.13. Result ID: 6996dcfd5698665ec4297141. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"30"}. This record does not assert independent reproduction. ### SPARSE Leakage: 68.13. Result ID: 6996dcfd5698665ec4297145. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"40"}. This record does not assert independent reproduction. ### PurMech Leakage: 68.63. Result ID: 6996dcfd5698665ec4297144. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"40"}. This record does not assert independent reproduction. ### LapMech Leakage: 68.85. Result ID: 6996dcfd5698665ec4297143. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"epsilon":"40"}. This record does not assert independent reproduction. ### Unprotected embedding Leakage: 77.35. Result ID: 6996dcfd5698665ec4297146. [Reporting paper]() Recorded evaluation configuration: {"epsilon":"infinity"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.