PPLX detector
pplx+cpu-int8 PII detection benchmark
Measured on 9 of 41 retained datasets under the same frozen scoring and masking protocol.
93.12%fully hidden annotations
96.34%detected / overlapped
13.53%extra masking
—CPU characters / second
Strengths
Highest complete-masking rates by normalized data type.
Dates & times99.95%1,860 / 1,861
Logins & usernames99.82%8,775 / 8,791
Other sensitive attributes99.55%223 / 224
Watch list
Lowest observed complete-masking rates; inspect before deployment.
Organizations27.61%1,261 / 4,568
Addresses & locations93.27%8,308 / 8,907
Customer & employee IDs93.62%1,703 / 1,819
Language coverage
The overall leader can differ from the best choice for one language slice.
| Language | Datasets | Fully hidden ↑ | Detected ↑ | Extra masking ↓ |
|---|---|---|---|---|
| English | 4 | 81.98% | 86.30% | 16.89% |
| Russian | 4 | 95.83% | 99.17% | 4.23% |
| Multilingual | 1 | 98.80% | 99.00% | — |
Configuration, source and version
- Family
- PPLX
- Revision
- f1f90a53823f5df0a1344c1e137d9fffdaab54d6
- Eligible datasets
- 9 / 41
- Character F1
- 0.698
- Untouched diagnostic
- 3.66% · 2,639 / 72,095
- Benchmark version
- 1.0.3 · 2026-09-09
- CPU seconds / 10k chars
- Not measured
- GPU seconds / 10k chars
- Not measured
Results by dataset
Complete masking is primary; detection shows whether any character overlapped.
| Dataset | Gold annotations | Fully hidden ↑ | Detected ↑ | Extra masking ↓ |
|---|---|---|---|---|
| tab-echr | 3,830 | 47.91% | 57.31% | — |
| secrets-issues | 288 | 81.25% | 100.00% | 18.81% |
| redmadrobot | 5,516 | 87.71% | 94.31% | 4.07% |
| nemotron-pii | 9,391 | 92.91% | 95.55% | 13.67% |
| ameau01 | 2,242 | 94.47% | 95.32% | 6.98% |
| nym-ru | 9,497 | 95.61% | 99.51% | — |
| synth-ru-tickets | 32,099 | 97.19% | 99.91% | — |
| hivetrace | 1,667 | 97.90% | 99.16% | 5.27% |
| kiji-multi | 7,565 | 98.80% | 99.00% | — |