Evaluate PII detector recall across curated sensitive data categories.
npx skills add https://github.com/wuyoscar/ISC-Bench --skill aiml-pii-benchmark
Please help me install this Agent Skill. Skill: aiml-pii-benchmark Source: https://github.com/wuyoscar/ISC-Bench/tree/main/templates/aiml_pii Command: npx skills add https://github.com/wuyoscar/ISC-Bench --skill aiml-pii-benchmark
This skill provides a structured benchmark framework for evaluating PII detectors on diverse, realistic data to ensure compliance and robustness.
Run the benchmark against your PII detector using the provided samples to obtain recall results.
High-intent search queries and answers about installing and using this skill.
To benchmark PII detectors for GDPR compliance, evaluate recall and precision across curated sensitive data categories in realistic contexts using a reproducible evaluation script applied to your detector endpoint.
Evaluating PII detection models uses recall, precision, and category coverage metrics computed by running a reproducible evaluation script against a detector endpoint using labeled datasets and PII regex patterns.
Compare multiple PII detection models by running an automated evaluation against curated realistic samples, ensuring dataset realism validation to report consistent recall and precision metrics across varied PII formats.
Testing PII detector robustness requires a dataset with category labels, PII regex patterns, a detector endpoint, and a reproducible evaluation script to accurately compute recall and category coverage.
PII detector benchmarking works for sensitive data in varied formats by validating dataset realism, ensuring PII appears in authentic embedding contexts to accurately evaluate detection recall and precision.
The best way to ensure PII appears in authentic contexts during compliance evaluation is through dataset realism validation, verifying sensitive data patterns vary correctly in format and embedding contexts before testing.
wuyoscarEvaluate a DistilBERT spam detector's recall across predefined social-media campaigns.
mvillmowEvaluate ML model performance on test datasets with classification and regression metrics.
framerslabDetect and redact personally identifiable information from text using regex, NLP, and NER.
manolakisAssess GDPR compliance, consent, retention, PII detection, and anonymization.
