Pseudonymization and Depseudonymization

1. generate keys

%%bash

logprep pseudo generate -f ./analyst 1024
logprep pseudo generate -f ./depseudo 2048

2. pseudonymize a string

%%bash

logprep pseudo pseudonymize ./analyst.crt ./depseudo.crt mystring

3. depseudonymize the string

%%bash

logprep pseudo depseudonymize ./analyst.key ./depseudo.key  < cyphertext from above >

Pseudonymizer Processor

import json
import uuid
from logprep.factory import Factory
from logprep.util.time import TimeParser
from logprep.ng.event.log_event import LogEvent
from logprep.ng.event.event_state import EventStateType
import logging
import sys

# Configure logging
logging.basicConfig(level=logging.DEBUG, stream=sys.stdout)

document = {
    "id": f"{uuid.uuid4()}",
    "@timestamp": str(TimeParser.now()),
    "user": {
        "name": "Hubert K. Kabal",
        "email": "kabal@example.com",
        "id": 12345,
    },
}

event = LogEvent(document, original=b"", state=EventStateType.RECEIVED)

print(f"Event before processing: {json.dumps(event.data, indent=2)}")

# Pseudonymization
config = {
    "almighty pseudonymizer": {
        "type": "ng_pseudonymizer",
        "pubkey_analyst": "./analyst.crt",
        "pubkey_depseudo": "./depseudo.crt",
        "regex_mapping": "../../../../../examples/exampledata/rules/pseudonymizer/regex_mapping.yml",
        "hash_salt": "a_secret_tasty_ingredient",
        "outputs": [
            {"opensearch": "pseudonyms"}
        ],
        "rules": [
            {
                "filter": "*",
                "pseudonymizer": {
                    "mapping": {
                        "user.name": "RE_WHOLE_FIELD",
                    }
                }
            }
        ],
        "max_cached_pseudonyms": 1000000
    }
}
processor = Factory.create(config)
processor.setup()
processor.process(event)

print(f"Event after processing: {json.dumps(event.data, indent=2)}")
print(f"{len(event.extra_data)=}")
print(f"Event extra data: {json.dumps(event.extra_data[0].data, indent=2)}")