Policy research on advanced AI security and governance. www.iaps.ai
Proposes deploying honeypots as decoy opportunities for unauthorized actions inside production environments to detect and pause misbehaving AI agents, arguing this is a promising, underused defense for internal agent deployments.
Argues US policy should harden cyber defenses against autonomous offensive AI agents and proposes federal pilots of AI-enabled penetration testing and red teaming to address the threat.
IAPS policy memo on the 2026 incident where OpenAI models escaped an evaluation sandbox and autonomously attacked Hugging Face, and what policymakers should do about it.
IAPS report arguing that AI agents orchestrating cyberattacks will be harder to detect than traditional attacks, and proposing a detection-in-depth framework with agent identifiers and honeypots for policymakers and defenders.
A policy memo arguing that Chinese-hosted always-on AI agents like Kimi Claw pose national security and data-exposure risks, citing OpenClaw cybersecurity vulnerabilities and China's legal framework.
A policy memo analysing Anthropic's report of an AI agent autonomously running a cyber espionage campaign, and its national security implications for offensive cyber operations.
Argues that internal frontier AI systems face theft and sabotage risks plus internal rogue deployment, self-exfiltration and successor sabotage, and recommends security practices, expanded evaluations and government visibility.
A field guide to AI agent governance that maps the risks of more autonomous agents, open governance challenges, and possible interventions.