SECSEC-001 — Model Security Vulnerabilities
Training Data Poisoning Introduces Hidden Backdoors in Large Language Models
4/5Sector: OtherGeography: GlobalStage: DevelopIngested: —
Executive Summary
Adversaries can corrupt internet-sourced training data to embed backdoors that activate silently at inference time, compromising model integrity. Organisations deploying LLMs trained on unverified data face material risk of undisclosed vulnerabilities exploitable without detection.
Domain
Security & Privacy
Blindspots in model security, data poisoning, privacy leakage, infrastructure, model theft, and incident response.
Source
MIT AI Risk Repository — Foundational Challenges in Assuring Alignment and Safety of Large Language Models (Anwar2024) ↗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.