AI Integrity: Defending Against Backdoors and Secret Loyalties
It highlights a neglected security problem for AI systems, particularly relevant to national security stakeholders.
The paper argues that AI integrity, ensuring AI systems are free from secret modifications, is an underappreciated pillar of AI security compared to confidentiality and availability, with significant implications for national security.
AI integrity means ensuring AI systems are free from secret or unauthorized modifications that could compromise their behavior. Integrity represents one pillar of the confidentiality, integrity, and availability (CIA) triad in information security: confidentiality preserves secrecy of sensitive information, integrity ensures data remain authentic and uncorrupted, and availability keeps systems operational when needed. While confidentiality receives some attention through efforts like RAND's Securing AI Model Weights report, and availability is naturally prioritized by market forces, AI integrity receives insufficient attention despite its importance to national security.