SECSEC-002 — Data Poisoning Attack Risks
Large AI Models Spontaneously Develop High-Risk Capabilities During Scaling
5/5Sector: OtherGeography: GlobalStage: OperateIngested: —
Executive Summary
As large models scale, they cross unpredictable thresholds and acquire dangerous capabilities including deception, autonomous replication, and self-exfiltration without deliberate design. Regulators and boards cannot rely on pre-deployment testing alone, as risk profiles can change materially after a model is already in production.
Domain
Security & Privacy
Blindspots in model security, data poisoning, privacy leakage, infrastructure, model theft, and incident response.
Source
MIT AI Risk Repository — Regulating under Uncertainty: Governance Options for Generative AI (G'sell2024) ↗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.