Red-Team an Image-Classification Pipeline for a Banking KYC Workflow
Overview
What this challenge is about.
Run FGSM, PGD, and transfer attacks on a banking KYC classifier, then identify top failure patterns. Get a verifiable certificate.
The scenario
The bank (around 9,000 staff, around 5 million retail customers in Ireland and the UK) processes about 12,000 KYC checks per day; a public-grade adversarial failure would trigger a regulatory disclosure to the Central Bank.
The Brief
What you'll do, and what you'll demonstrate.
Quantify the production KYC image classifier's robustness to standard adversarial attacks and recommend three remediations.
Earning criteria — what you'll demonstrate
- Implement and apply standard adversarial attacks to a real classifier
- Quantify robust accuracy at standard threat-model budgets
- Identify failure patterns and translate them into remediation plans
- Communicate adversarial-robustness findings to a non-research risk committee
Program Fit
Where this fits in your program.
Sharpens the same skills your degree expects you to demonstrate.
Trustworthy AI, Robustness, and Safety
Master · Responsible Ai
Strong alignment
This challenge maps to Trustworthy AI, Robustness, and Safety at the Master level. It sharpens the same practical skills your coursework expects — but in a real industry context with actual constraints and deliverables.
Skills
Skills you'll demonstrate.
Each one shows up on your verified credential.
- Adversarial Attacks
Apply adversarial attacks to solve real industry problems and demonstrate production-level capability.
- Robust Evaluation
Apply robust evaluation to solve real industry problems and demonstrate production-level capability.
- Red Teaming
Apply red teaming to solve real industry problems and demonstrate production-level capability.
- Threat Modeling
Apply threat modeling to solve real industry problems and demonstrate production-level capability.
- Pytorch
Apply pytorch to solve real industry problems and demonstrate production-level capability.
- Risk Assessment
Apply risk assessment to solve real industry problems and demonstrate production-level capability.
Careers
Career paths this challenge builds toward
Completing this challenge demonstrates skills that transfer directly to these roles:
AI Safety Researcher
Red-teaming a production classifier with rigorous robust-accuracy measurement and a remediation memo is the textbook AI safety researcher's project at any regulated AI deployment.
This challenge sharpens
- adversarial-attacks
- robust-evaluation
- red-teaming
ML Researcher
Implementing and benchmarking adversarial attacks against a real model with publication-grade rigor is core ML-researcher craft.
This challenge sharpens
- adversarial-attacks
- robust-evaluation
- pytorch
Applied AI Scientist
Translating attack findings into a remediation plan that engineering can ship is the applied-AI scientist's daily work in regulated industries.
This challenge sharpens
- red-teaming
- risk-assessment
- robust-evaluation