PII

PII Detection evaluates text to identify the presence of personally identifiable information. This evaluation is crucial for ensuring privacy and compliance with data protection regulations by detecting and managing sensitive information in text data. 

result = evaluator.evaluate(
    eval_templates="pii",
    inputs={
        "input": "My name is John Doe."
    },
    model_name="turing_flash"
)

print(result.eval_results[0].output)
print(result.eval_results[0].reason)
import { Evaluator, Templates } from "@future-agi/ai-evaluation";

const evaluator = new Evaluator();

const result = await evaluator.evaluate(
  "pii",
  {
    input: "My name is John Doe."
  },
  {
    modelName: "turing_flash",
  }
);

console.log(result);
Input
Required InputTypeDescription
inputstringThe text content to be analysed for PII.
Output
FieldDescription
ResultReturns Passed if no PII is detected, or Failed if PII is detected.
ReasonProvides a detailed explanation of why the content was classified as containing or not containing PII.

What to do when PII is Detected

When PII is detected, several measures can be taken to ensure privacy protection and regulatory compliance. The first step is redaction, which involves removing or masking the identified PII using techniques such as replacing sensitive information with placeholders or anonymising data.

Effective data handling practices should also be implemented to manage and safeguard PII, ensuring adherence to data protection regulations like GDPR and CCPA. Additionally, system adjustments can enhance PII detection accuracy by refining detection mechanisms, reducing false positives, and regularly updating detection patterns and models to adapt to evolving PII types and formats.

Comparing PII Detection with Similar Evals

  • Data Privacy Compliance: PII Detection identifies specific types of personal information within text, while Data Privacy Compliance has a broader scope, ensuring that data handling practices align with privacy regulations like GDPR and HIPAA.
  • Bias Detection: PII Detection targets sensitive personal information in output, while Bias Detection identifies gender, racial, cultural, or ideological bias in content.
Was this page helpful?

Questions & Discussion