Research release on empirically validated toolkit for measuring AI manipulation capabilities, tested across 10,000+ participants in finance and health domains. Provides open-source methodology and materials for evaluating how AI systems can be misused to deceptively influence human behavior and beliefs in high-stakes scenarios.

IH-Challenge is a training framework that teaches models to respect instruction hierarchy and distinguish between trusted vs. untrusted inputs, improving robustness against prompt injection attacks and enhancing safety steerability. This is practically useful for engineers building production AI systems that need stronger defenses against adversarial inputs.