Search papers, labs, and topics across Lattice.
This study evaluates the capability of frontier AI agents to autonomously conduct structured security audits of clinical AI models, addressing the critical need for identifying adversarial vulnerabilities that could harm patients. Using a standardized evaluation task, agents were tested on their ability to implement attacks, compute a Security Posture Score, and generate structured reports based solely on written instructions and a bash interface. The results revealed that while Claude Sonnet 4.6 and GPT-4.1 successfully completed all tasks with perfect scores, GPT-4o struggled significantly, highlighting disparities in performance and efficiency among different AI models.
Frontier AI agents can autonomously conduct clinical security audits, but not all models perform equally, revealing significant efficiency gaps.
Clinical AI models can expose patients to harm when adversarial vulnerabilities go undetected, yet formal security auditing requires statistical expertise, specialized tools, and significant time. We present an open evaluation task, built on METR Task Standard v0.3.0, that tests whether frontier AI agents can autonomously implement a structured clinical AI security audit. Given a pre-trained clinical prediction model, a patient dataset, and written instructions, each agent must implement four attacks from pseudocode, compute a Security Posture Score covering FGSM robustness, membership inference resistance, expected calibration error, and boundary attack resistance, and write a structured JSON report in a Docker container using only a bash interface and no scaffolding code. Six variants span the Wisconsin Diagnostic Breast Cancer and MIMIC-IV ICU mortality datasets across three model architectures with increasing defense strength, with reference scores from 55.60 to 90.41. We ran 54 evaluations across three frontier models, with three runs per variant. Claude Sonnet 4.6 and GPT-4.1 completed all 18 runs and received perfect evaluator scores. GPT-4o completed 61 percent of runs and used about five times the per-run token count of Claude, although provider tokenization differs. Total API costs were 8 US dollars for GPT-4.1, 12 US dollars for Claude Sonnet 4.6, and 27 US dollars for GPT-4o. GPT-4o failures involved premature session termination, an aggregation error, and an empty submission file. The task, scoring infrastructure, and Wisconsin Breast Cancer assets are publicly released; MIMIC-IV variants require separate PhysioNet access.
