Robustness tests for biomedical foundation models should tailor to specification

Existing regulatory frameworks for biomedical AI include robustness as a key component but lack detailed implementational guidance. The recent rise of biomedical foundation models creates new hurdles in testing and certification given their broad capabilities and susceptibility to complex distribution shifts. To balance test feasibility and effectiveness, we suggest a priority-based, task-oriented approach to tailor robustness evaluation objectives to a predefined specification. We urge concrete policies to adopt a granular categorization of robustness concepts in the specification. The approach promotes the standardization of risk assessment and monitoring and guides technical developments and mitigation efforts.

Keywords: foundation model, health AI, robustness, AI policy

JEL Classification: I18, C52

Suggested Citation: Suggested Citation

Xian, R. Patrick and Baker, Noah R. and David, Tom and Cui, Qiming and Holmgren, A. Jay and Bauer, Stefan and Sushil, Madhumita and Abbasi-Asl, Reza, Robustness tests for biomedical foundation models should tailor to specification (January 06, 2025). Available at SSRN: https://ssrn.com/abstract=5013799 or http://dx.doi.org/10.2139/ssrn.5013799