SECSEC-001 — Model Security Vulnerabilities
Generative AI Model Exposes Sensitive Personal Data Used in Training
4/5Sector: OtherGeography: GlobalStage: OperateIngested: —
Executive Summary
Generative AI systems can be induced to reproduce personally identifiable information and medical records embedded in their training data. Organisations face regulatory liability and reputational harm where such disclosures breach data protection obligations.
Domain
Security & Privacy
Blindspots in model security, data poisoning, privacy leakage, infrastructure, model theft, and incident response.
Source
MIT AI Risk Repository — Generative AI Misuse: A Taxonomy of Tactics and Insights from Real-World Data (Marchal2024) ↗https://airisk.mit.edu/
Could this happen in your organisation?
A Velinor AI Audit maps your active AI portfolio against the 50+ blindspots and benchmarks against documented sector failures like this one. A board-ready foresight document in 5 weeks.