Skip to main content
Back to challenges
Challenge

Crisis Zone Data Privacy Auditor with Mastra AI

Addressing concerns in The Lancet Digital Health regarding ethical data collection during aid shortages, this challenge asks developers to construct an automated privacy audit agent. Using Mastra AI, participants will build TypeScript agents that intercept data collection streams from field surveys, perform automated leak checks for sensitive spatial coordinates and biometric traits, and enforce privacy-preserving transformations.

Data ScienceHosted by Vera
Sign in free to start
Challenge brief

What you are building

The core problem, expected build, and operating context for this challenge.

Build an ethical data privacy auditing agent for humanitarian data collection using Mastra AI in TypeScript.

Delivery guide

How work is evaluated

Evaluation

Evaluates privacy compliance checking and coordinate blurring precision.

Datasets

Challenge datasets

Public datasets, plus the private datasets you have access to.

Evaluation rubric

How submissions are scored

These dimensions define what the evaluator checks and which criteria separate a passable run from a strong one.

Dimensions
2 scoring checks
Binary
2 pass or fail dimensions
Ordinal
0 scaled dimensions
Dimension 1

check_no_exact_coords

Ensure exact float lat/lon coordinates are stripped from output

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Dimension 2

privacy_compliance_score

Percentage of re-identification vectors successfully suppressed • target: 0.95 • range: 0-1

Binary check

This dimension contributes its full weight only when the submission satisfies the requirement. Partial credit is not awarded.

Learning goals

What you should walk away with

  • Implement real-time field data privacy auditing workflows using Mastra AI

  • Identify high-risk spatial-temporal trajectory markers that risk re-identification

  • Apply localized spatial blurring and differential noise addition

  • Generate ethical compliance certification logs prior to central server upload

Resources and assets

Reference links and supporting material

Dataset notes

Synthetic crisis region survey responses containing unblurred GPS locations, named entities, and demographic traits.

Challenge setup

Evaluates privacy compliance checking and coordinate blurring precision.

Challenge input

JSON containing survey_id, latitude, longitude, vulnerability_notes

Mastra AI

Mandatory Mastra AI framework

Evaluated output

JSON containing is_compliant (bool), redacted_notes (string), spatial_grid_cell (string)

Evaluation checks
  • Ensure exact float lat/lon coordinates are stripped from output
  • Percentage of re-identification vectors successfully suppressed • target: 0.95 • range: 0-1
Configured evaluation evidence
  • Benchmark: PrivEval-Humanitarian
  • Privacy Compliance Score target: 0.95
  • 1 public reference case
Configured runtime
  • JavaScript execution harness
  • javascript sandbox (unavailable on Versalist)

Summary shows the first task, up to three tools, and up to three evidence items. Open the technical recipe to view all configured items.

View technical recipe

Configured tools

Action Space
  • Mastra AI · Required
  • sktime · Optional
  • Nvidia · Optional
Orchestration
  • Mastra AI · Required

Evaluation contract

  • check_no_exact_coords · Weight 1
  • privacy_compliance_score · Weight 1

Metrics

  • privacy_compliance_score · Target 0.95

Benchmarks

  • PrivEval-Humanitarian
  • security

Reference cases

  • 1 public reference case

Workflow tasks

  1. Task 1

    Input: JSON containing survey_id, latitude, longitude, vulnerability_notes

    Output: JSON containing is_compliant (bool), redacted_notes (string), spatial_grid_cell (string)

    Execution harness: JavaScript

Evaluation tools

  • Mastra AI · Agent Framework

Recipe freeze marker

No recipe freeze time is recorded.

Frequently Asked Questions about Crisis Zone Data Privacy Auditor with Mastra AI