SECSEC-001 — Model Security Vulnerabilities
Training Data Poisoning and Backdoor Triggers in Large Language Models
4/5Sector: TechnologyGeography: GlobalStage: DevelopIngested: —
Executive Summary
Adversaries can corrupt LLM behaviour by injecting malicious data during training, embedding hidden triggers that activate on command without detection. Firms deploying third-party or open-source models face undisclosed material risk to output integrity, with direct implications for SEC disclosure obligations around AI system security.
Domain
Security & Privacy
Blindspots in model security, data poisoning, privacy leakage, infrastructure, model theft, and incident response.
Source
MIT AI Risk Repository — Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systems (Cui2024) ↗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.