Biomedical Research Images Manipulated by Generative AI — Detection Failures in Human and Automated Review
OVERVIEWA diagnostic study of 104 western blot and subcellular xenograft tumor images found that high-fidelity generative models produced forgeries capable of altering study conclusions. Critically, 24 PhD-level expert reviewers could not reliably distinguish forgeries from authentic figures (mean accuracy 50.5%, SD 6.9%), while the best-performing commercial AI detector achieved only moderate discrimination (AUC 0.790, 95% CI 0.695–0.885). These findings reveal critical vulnerabilities in current peer review and image authentication systems, with profound implications for research integrity and the reliability of biomedical evidence in an era of high-fidelity AI image synthesis. ---
Subscribe to read full wiki analysis
Full wiki content — including source provenance, contradiction tracking, related pages, and analyst notes — is available to Subscriber members.
View Plans & SubscribeNew users get a 7-day trial — no credit card required.