# Cross-Input Privacy Leakage on memory\_ehr

Source: [Cross-Input Privacy Leakage on memory\_ehr](<https://www.sota2.com/research/sota/cross-input-privacy-leakage-on-memory_ehr>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-25T13:10:10.008Z

Evaluation of cross-input privacy leakage detection on the memory\_ehr dataset, measured using metrics such as RN, EN, EE, CER, AER, and ExecErr.

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 | Cross-Input Privacy Leakage |
| Dataset (including any stated split) | memory\_ehr |
| Metric | RN |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 3 of 3 |
| 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

- [RN](<https://www.sota2.com/research/sota/cross-input-privacy-leakage-on-memory_ehr.md?metric=RN>): Lower is better; unit: SCALAR.

- [EN](<https://www.sota2.com/research/sota/cross-input-privacy-leakage-on-memory_ehr.md?metric=EN>): Lower is better; unit: SCALAR.

- [EE](<https://www.sota2.com/research/sota/cross-input-privacy-leakage-on-memory_ehr.md?metric=EE>): Lower is better; unit: PERCENT.

- [CER](<https://www.sota2.com/research/sota/cross-input-privacy-leakage-on-memory_ehr.md?metric=CER>): Lower is better; unit: PERCENT.

- [AER](<https://www.sota2.com/research/sota/cross-input-privacy-leakage-on-memory_ehr.md?metric=AER>): Lower is better; unit: PERCENT.

- [ExecErr](<https://www.sota2.com/research/sota/cross-input-privacy-leakage-on-memory_ehr.md?metric=ExecErr>): Lower is better; unit: PERCENT.

## Recorded results

| Method | RN | Result date | Report paper |
| --- | --- | --- | --- |
| MiniMax-M2.5 | 55 | Not recorded | 69c36c040636e5bf4afc64a4 |
| qwen3.5-plus | 55 | Not recorded | 69c36c040636e5bf4afc64a4 |
| DeepSeek | 55 | Not recorded | 69c36c040636e5bf4afc64a4 |

### MiniMax-M2.5

RN: 55. Result ID: 69c3deb047f34ce924ad48ed.

[Reporting paper](<https://www.sota2.com/research/paper/69c36c040636e5bf4afc64a4.md>)

Recorded evaluation configuration: {"Provider":"MiniMax-M2.5"}. This record does not assert independent reproduction.

### qwen3.5-plus

RN: 55. Result ID: 69c3deb047f34ce924ad48ee.

[Reporting paper](<https://www.sota2.com/research/paper/69c36c040636e5bf4afc64a4.md>)

Recorded evaluation configuration: {"Provider":"qwen3.5-plus"}. This record does not assert independent reproduction.

### DeepSeek

RN: 55. Result ID: 69c3deb047f34ce924ad48ef.

[Reporting paper](<https://www.sota2.com/research/paper/69c36c040636e5bf4afc64a4.md>)

Recorded evaluation configuration: {"Provider":"DeepSeek"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
