# Membership Inference Advantage Bounding on Uniform prior size 100 Source: [Membership Inference Advantage Bounding on Uniform prior size 100]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:34:42.506Z Evaluation of Membership Inference Advantage Bounding techniques using a synthetic dataset characterized by a uniform prior distribution of size 100. 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 100 | | Metric | Advantage Upper Bound | | Unit | PERCENT | | Direction | Lower 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](): Lower is better; unit: PERCENT. ## Recorded results | Method | Advantage Upper Bound | Result date | Report paper | | --- | --- | --- | --- | | ReRo bound | 1.2 | Not recorded | 68fa71011e209131cea4e7b7 | | ReRo bound | 1.8 | Not recorded | 68fa71011e209131cea4e7b7 | | ReRo bound | 2.4 | Not recorded | 68fa71011e209131cea4e7b7 | | ReRo bound | 3.5 | Not recorded | 68fa71011e209131cea4e7b7 | | Guo et al. (2022b) (MC) | 4.9 | Not recorded | 68fa71011e209131cea4e7b7 | | Guo et al. (2022b) (MC) | 6.2 | Not recorded | 68fa71011e209131cea4e7b7 | | Guo et al. (2022b) | 7.6 | Not recorded | 68fa71011e209131cea4e7b7 | | ReRo bound | 7.7 | Not recorded | 68fa71011e209131cea4e7b7 | | Guo et al. (2022b) (MC) | 8.1 | Not recorded | 68fa71011e209131cea4e7b7 | | Guo et al. (2022b) | 9.7 | Not recorded | 68fa71011e209131cea4e7b7 | | Guo et al. (2022b) (MC) | 12 | Not recorded | 68fa71011e209131cea4e7b7 | | Guo et al. (2022b) | 13.1 | Not recorded | 68fa71011e209131cea4e7b7 | | Guo et al. (2022b) | 19.5 | Not recorded | 68fa71011e209131cea4e7b7 | | Guo et al. (2022b) (MC) | 21 | Not recorded | 68fa71011e209131cea4e7b7 | | Guo et al. (2022b) | 34.6 | Not recorded | 68fa71011e209131cea4e7b7 | | ReRo bound | 36.2 | Not recorded | 68fa71011e209131cea4e7b7 | | Guo et al. (2022b) (MC) | 54.9 | Not recorded | 68fa71011e209131cea4e7b7 | | Guo et al. (2022b) | 86.1 | Not recorded | 68fa71011e209131cea4e7b7 | ### ReRo bound Advantage Upper Bound: 1.2. Result ID: 699184de3a6c31484908b04c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":3}. This record does not assert independent reproduction. ### ReRo bound Advantage Upper Bound: 1.8. Result ID: 699184de3a6c31484908b04b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":2.5}. This record does not assert independent reproduction. ### ReRo bound Advantage Upper Bound: 2.4. Result ID: 699184de3a6c31484908b04a. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":2}. This record does not assert independent reproduction. ### ReRo bound Advantage Upper Bound: 3.5. Result ID: 699184de3a6c31484908b049. [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: 4.9. Result ID: 699184de3a6c31484908b046. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":3,"Monte-Carlo approximation":true}. This record does not assert independent reproduction. ### Guo et al. (2022b) (MC) Advantage Upper Bound: 6.2. Result ID: 699184de3a6c31484908b045. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":2.5,"Monte-Carlo approximation":true}. This record does not assert independent reproduction. ### Guo et al. (2022b) Advantage Upper Bound: 7.6. Result ID: 699184de3a6c31484908b040. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":3}. This record does not assert independent reproduction. ### ReRo bound Advantage Upper Bound: 7.7. Result ID: 699184de3a6c31484908b048. [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: 8.1. Result ID: 699184de3a6c31484908b044. [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: 9.7. Result ID: 699184de3a6c31484908b03f. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":2.5}. This record does not assert independent reproduction. ### Guo et al. (2022b) (MC) Advantage Upper Bound: 12. Result ID: 699184de3a6c31484908b043. [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: 13.1. Result ID: 699184de3a6c31484908b03e. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":2}. This record does not assert independent reproduction. ### Guo et al. (2022b) Advantage Upper Bound: 19.5. Result ID: 699184de3a6c31484908b03d. [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: 21. Result ID: 699184de3a6c31484908b042. [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: 34.6. Result ID: 699184de3a6c31484908b03c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":1}. This record does not assert independent reproduction. ### ReRo bound Advantage Upper Bound: 36.2. Result ID: 699184de3a6c31484908b047. [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: 54.9. Result ID: 699184de3a6c31484908b041. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":0.5,"Monte-Carlo approximation":true}. This record does not assert independent reproduction. ### Guo et al. (2022b) Advantage Upper Bound: 86.1. Result ID: 699184de3a6c31484908b03b. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"sigma":0.5}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.