piiscan / training /rule-eval.json
vectorsense's picture
Publish PiiScan
bc64c0f verified
Raw History Blame Contribute Delete
4.76 kB
{
"test_file": "C:\\git\\poc\\hf-pii-phi-identifier\\prepared-training-data\\test.jsonl",
"tier_filter": null,
"rows_by_tier": {
"held_out_same_generator": 8201,
"external_human_annotated": 127
},
"rule_supported_types": [
"EMAIL_ADDRESS",
"IP_ADDRESS",
"PAYMENT_CARD_NUMBER",
"PHONE_NUMBER",
"TAX_ID",
"URL"
],
"gated_types": [
"EMAIL_ADDRESS",
"IP_ADDRESS",
"PAYMENT_CARD_NUMBER",
"PHONE_NUMBER",
"TAX_ID"
],
"micro_over_supported_types": {
"precision": 0.9753,
"recall": 0.5888,
"f1": 0.7343
},
"gate_micro_excluding_experimental": {
"precision": 0.9764,
"recall": 0.5888,
"f1": 0.7346
},
"per_type": {
"AGE": {
"tp": 0,
"fp": 0,
"fn": 2991,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"rule_supported": false,
"tier": "model_trained"
},
"CITY": {
"tp": 0,
"fp": 0,
"fn": 4146,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"rule_supported": false,
"tier": "model_trained"
},
"DATE_TIME": {
"tp": 0,
"fp": 0,
"fn": 9592,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"rule_supported": false,
"tier": "model_trained"
},
"DRIVER_LICENSE_NUMBER": {
"tp": 0,
"fp": 0,
"fn": 1662,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"rule_supported": false,
"tier": "model_trained"
},
"EMAIL_ADDRESS": {
"tp": 4258,
"fp": 56,
"fn": 142,
"precision": 0.987,
"recall": 0.9677,
"f1": 0.9773,
"rule_supported": true,
"tier": "model_trained"
},
"GOVERNMENT_ID": {
"tp": 0,
"fp": 0,
"fn": 3439,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"rule_supported": false,
"tier": "model_trained"
},
"IP_ADDRESS": {
"tp": 0,
"fp": 2,
"fn": 0,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"rule_supported": true,
"tier": "rule_only"
},
"PASSPORT_NUMBER": {
"tp": 0,
"fp": 0,
"fn": 1260,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"rule_supported": false,
"tier": "model_trained"
},
"PAYMENT_CARD_NUMBER": {
"tp": 132,
"fp": 6,
"fn": 1762,
"precision": 0.9565,
"recall": 0.0697,
"f1": 0.1299,
"rule_supported": true,
"tier": "model_trained"
},
"PERSON_NAME": {
"tp": 0,
"fp": 0,
"fn": 8810,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"rule_supported": false,
"tier": "model_trained"
},
"PHONE_NUMBER": {
"tp": 2202,
"fp": 95,
"fn": 1159,
"precision": 0.9586,
"recall": 0.6552,
"f1": 0.7784,
"rule_supported": true,
"tier": "model_trained"
},
"POSTAL_CODE": {
"tp": 0,
"fp": 0,
"fn": 2566,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"rule_supported": false,
"tier": "model_trained"
},
"STREET_ADDRESS": {
"tp": 0,
"fp": 0,
"fn": 3909,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"rule_supported": false,
"tier": "model_trained"
},
"TAX_ID": {
"tp": 0,
"fp": 0,
"fn": 1540,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"rule_supported": true,
"tier": "model_trained"
},
"URL": {
"tp": 1,
"fp": 8,
"fn": 1,
"precision": 0.1111,
"recall": 0.5,
"f1": 0.1818,
"rule_supported": true,
"tier": "experimental"
},
"USERNAME": {
"tp": 0,
"fp": 0,
"fn": 8,
"precision": 0.0,
"recall": 0.0,
"f1": 0.0,
"rule_supported": false,
"tier": "experimental"
}
},
"false_positive_examples": {
"EMAIL_ADDRESS": [
"\u8bf7\u5404\u4f4d\u540c\u4e8b\u5c06\u53cd\u9988\u8868\u53d1\u9001\u81f3LI41@gmail.com",
"\u8054\u7cfb\u90ae\u7bb1\u4e3a\u5fe0@aol.com",
"\u90ae\u7bb1LV@protonmail.com"
],
"PHONE_NUMBER": [
"8063-781-5710",
"03 11440",
"120-0044"
],
"PAYMENT_CARD_NUMBER": [
"5640366405299991",
"561027-1819915",
"451117-2991020"
],
"URL": [
"www.example.com",
"https://claim.example.com",
"https://hr.example.com"
],
"IP_ADDRESS": [
"192.168.1.1",
"68.16.58.16"
]
}
}