# Membership Inference Advantage Bounding on Uniform prior size 10 Source: [Membership Inference Advantage Bounding on Uniform prior size 10]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:34:42.490Z Evaluation of Membership Inference Advantage Bounding performance using a dataset defined by a Uniform prior of size 10, measured by the resulting upper bound on the advantage. 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 | Membership Inference Advantage Bounding | | Dataset (including any stated split) | Uniform prior size 10 | | Metric | Advantage Upper Bound | | Unit | SCALAR | | Direction | Higher is better | | Results loaded | 18 of 18 | | 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 - [Advantage Upper Bound](): Higher is better; unit: SCALAR. ## Recorded results | Method | Advantage Upper Bound | Result date | Report paper | | --- | --- | --- | --- | | Guo et al. (2022b) | 0.976 | Not recorded | 68fa71011e209131cea4e7b7 | | Guo et al. (2022b) (MC) | 0.771 | Not recorded | 68fa71011e209131cea4e7b7 | | ReRo bound | 0.737 | Not recorded | 68fa71011e209131cea4e7b7 | | Guo et al. (2022b) | 0.593 | Not recorded | 68fa71011e209131cea4e7b7 | | Guo et al. (2022b) (MC) | 0.397 | Not recorded | 68fa71011e209131cea4e7b7 | | Guo et al. (2022b) | 0.38 | Not recorded | 68fa71011e209131cea4e7b7 | | ReRo bound | 0.322 | Not recorded | 68fa71011e209131cea4e7b7 | | Guo et al. (2022b) | 0.274 | Not recorded | 68fa71011e209131cea4e7b7 | | Guo et al. (2022b) (MC) | 0.257 | Not recorded | 68fa71011e209131cea4e7b7 | | Guo et al. (2022b) | 0.213 | Not recorded | 68fa71011e209131cea4e7b7 | | ReRo bound | 0.189 | Not recorded | 68fa71011e209131cea4e7b7 | | Guo et al. (2022b) (MC) | 0.184 | Not recorded | 68fa71011e209131cea4e7b7 | | Guo et al. (2022b) | 0.174 | Not recorded | 68fa71011e209131cea4e7b7 | | Guo et al. (2022b) (MC) | 0.144 | Not recorded | 68fa71011e209131cea4e7b7 | | ReRo bound | 0.128 | Not recorded | 68fa71011e209131cea4e7b7 | | Guo et al. (2022b) (MC) | 0.118 | Not recorded | 68fa71011e209131cea4e7b7 | | ReRo bound | 0.099 | Not recorded | 68fa71011e209131cea4e7b7 | | ReRo bound | 0.08 | Not recorded | 68fa71011e209131cea4e7b7 | ### Guo et al. (2022b) Advantage Upper Bound: 0.976. Result ID: 699184de3a6c31484908b029. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":0.5}. This record does not assert independent reproduction. ### Guo et al. (2022b) (MC) Advantage Upper Bound: 0.771. Result ID: 699184de3a6c31484908b02f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":0.5,"Monte-Carlo approximation":true}. This record does not assert independent reproduction. ### ReRo bound Advantage Upper Bound: 0.737. Result ID: 699184de3a6c31484908b035. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":0.5}. This record does not assert independent reproduction. ### Guo et al. (2022b) Advantage Upper Bound: 0.593. Result ID: 699184de3a6c31484908b02a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":1}. This record does not assert independent reproduction. ### Guo et al. (2022b) (MC) Advantage Upper Bound: 0.397. Result ID: 699184de3a6c31484908b030. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":1,"Monte-Carlo approximation":true}. This record does not assert independent reproduction. ### Guo et al. (2022b) Advantage Upper Bound: 0.38. Result ID: 699184de3a6c31484908b02b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":1.5}. This record does not assert independent reproduction. ### ReRo bound Advantage Upper Bound: 0.322. Result ID: 699184de3a6c31484908b036. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":1}. This record does not assert independent reproduction. ### Guo et al. (2022b) Advantage Upper Bound: 0.274. Result ID: 699184de3a6c31484908b02c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":2}. This record does not assert independent reproduction. ### Guo et al. (2022b) (MC) Advantage Upper Bound: 0.257. Result ID: 699184de3a6c31484908b031. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":1.5,"Monte-Carlo approximation":true}. This record does not assert independent reproduction. ### Guo et al. (2022b) Advantage Upper Bound: 0.213. Result ID: 699184de3a6c31484908b02d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":2.5}. This record does not assert independent reproduction. ### ReRo bound Advantage Upper Bound: 0.189. Result ID: 699184de3a6c31484908b037. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":1.5}. This record does not assert independent reproduction. ### Guo et al. (2022b) (MC) Advantage Upper Bound: 0.184. Result ID: 699184de3a6c31484908b032. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":2,"Monte-Carlo approximation":true}. This record does not assert independent reproduction. ### Guo et al. (2022b) Advantage Upper Bound: 0.174. Result ID: 699184de3a6c31484908b02e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":3}. This record does not assert independent reproduction. ### Guo et al. (2022b) (MC) Advantage Upper Bound: 0.144. Result ID: 699184de3a6c31484908b033. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":2.5,"Monte-Carlo approximation":true}. This record does not assert independent reproduction. ### ReRo bound Advantage Upper Bound: 0.128. Result ID: 699184de3a6c31484908b038. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":2}. This record does not assert independent reproduction. ### Guo et al. (2022b) (MC) Advantage Upper Bound: 0.118. Result ID: 699184de3a6c31484908b034. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":3,"Monte-Carlo approximation":true}. This record does not assert independent reproduction. ### ReRo bound Advantage Upper Bound: 0.099. Result ID: 699184de3a6c31484908b039. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":2.5}. This record does not assert independent reproduction. ### ReRo bound Advantage Upper Bound: 0.08. Result ID: 699184de3a6c31484908b03a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":3}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.