Misaligned AI as a New Insider Risk
Apollo Research policy memo arguing that misaligned AI models deployed in high-stakes government and contractor settings should be treated as insider risk, and that existing insider-risk policies need adapting.
Research
Apollo Research
Understanding and evaluating deceptive AI. apolloresearch.ai
Focus All
Topic Security & misuse
Source Apollo Research · 6
Date Any time
1 item
1 item
NIST RFI: Security Considerations for AI Agents
Apollo Research's comment to NIST on agent security recommends scheming and misalignment evaluations, AI control and monitoring, and tighter oversight of high-stakes agentic deployments to prevent loss of control.
1 item
Seven Provisions in the National Defense Authorization Act with High Potential to Accelerate AI Security
Apollo Research reviews seven US NDAA provisions that could accelerate AI security, linking them to efforts against misalignment and scheming in high-stakes defense settings.
1 item
Assurance of Frontier AI Built for National Security
Policy memo giving US national-security agencies a roadmap to use scheming and control evaluations within AI assurance frameworks, treating scheming as a sign of low reliability and governability.
1 item
Capturing and Countering Threats to National Security: a Blueprint for an Agile AI Incident Regime
Proposes a three-part AI incident regime modeled on US incident response, so states can track national security threats from frontier AI and swiftly contain them.
1 item
Recommendations For The Next Stages Of The Frontier AI Taskforce
Apollo Research's policy recommendations to the UK Frontier AI Taskforce, urging it to act as an AI safety regulator and focus on national security and systemic risk.