Track 03

Scam Defence & Awareness

Help people recognise manipulation before they lose trust, money or access.

The challenge brief

What you are expected to build.

Agentic scam defence uses AI agents to investigate suspicious content, explain manipulation and guide people toward a safer decision. Build one agent, a coordinated multi-agent system or an agent-enabled app for SMS, email, URLs, QR codes, calls or fake documents—not merely a red or green warning label.

Minimum working outcome

A focused, testable scam-defence agent.

Deliver a working, testable prototype that lets a user submit suspicious content and receive an evidence-based assessment and safe next step. Your agent may call URL reputation, QR decoding, OCR, identity or reporting APIs; use Claude, Gemini or open-source models; or run locally to protect sensitive data. Show the checks and tools used, highlight the exact suspicious cues, state uncertainty and recommend verification, blocking or reporting actions. Demonstrate at least one scam case and one legitimate case, explain how false positives are handled and show how personal data is protected.

Your demonstration should include

01Problem & user

02Inputs & evidence

03Agent workflow

04Defensive action

05Human approval

06Result & limitations

Choose your challenge

Four project directions.

Explainable phishing detector

Analyse a message or email and highlight the exact cues behind its risk score.

QR and link safety agent

Decode a QR or URL, inspect redirects and explain whether the destination is trustworthy.

Scam reporting assistant

Collect evidence, redact sensitive data and prepare a structured report for review.

Adaptive awareness coach

Turn real scam patterns into short, personalised simulations and corrective guidance.

Data & references

Sample datasets—or use your own.

Use these as a starting point, bring your own permitted data or create a clearly documented synthetic dataset. Never test on systems or people without permission.

University of New Brunswick

Your submission should prove

The agent can observe, reason and defend—responsibly.

Clear problemWorking flow or prototypeEvidence of valueHuman oversightKnown limitations