Search bioRxiv⌕ Search
Home/Archive/bioRxiv

bioRxiv · 10.1101/2024.01.23.576647

Experts fail to reliably detect AI-generated histological data

Hartung, J.·Reuter, S.·Kulow, V. A.·Fahling, M.·Spreckelsen, C.·Mrowka, R.
View original source ↗Export metadata ↓

Abstract

AI-based methods to generate images have seen unprecedented advances in recent years challenging both image forensic and human perceptual capabilities. Accordingly, they are expected to play an increasingly important role in the fraudulent fabrication of data. This includes images with complicated intrinsic structures like histological tissue samples, which are harder to forge manually. We use stable diffusion, one of the most recent generative algorithms, to create such a set of artificial histological samples and in a large study with over 800 participants, we study the ability of human subjects to discriminate between such artificial and genuine histological images. Although they perform better than naive participants, we find that even experts fail to reliably identify fabricated data. While participant performance depends on the amount of training data used, even low quantities result in convincing images, necessitating methods to detect fabricated data and technical standards such as C2PA to secure data integrity.

Source connections

Explore related subjects

scientific communication and educationPreprint

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Hartung, J., Reuter, S., Kulow, V. A., Fahling, M., Spreckelsen, C., Mrowka, R.. 2024-01-25. Experts fail to reliably detect AI-generated histological data. https://doi.org/10.1101/2024.01.23.576647

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related preprints

bioRxiv2026

Auditing Biomedical Literature with Blinded AI Peer Review: Where Peer Review Works, Where It Fails, and How to Strengthen It

Biomedical publishing has grown more than elevenfold since 1991, outstripping human peer review. Unblinded language models cannot audit this literature objectively because they recognize famous authors and journals from training memory. We built BARS (Blinded AI Review System), an automated referee that strips titles, author names, institutions, journal headers, and dates before grading full-text manuscripts on a 10-point scale covering methods, evidence, biology, and reproducibility. We used BARS to generate 1,874 blind reviews across 1,714 unique papers. BARS passed 100% of verified sound controls, caught 77% to 91% of internally flawed papers, eliminated a +0.35-point prestige boost, and more than doubled human referee consistency. Across 320 recent open-access articles (2020-2025) from eight fields, 54% failed on core scientific rigor (<5.0/10; 41% excluding megajournals). Revision at selective journals improved preprints more than twice as much as revision at commercial megajournals (+0.62 vs. +0.30 points; baseline-adjusted p = 0.033), and BARS recalled 98% of unresolved human referee critiques across 100 open-review papers. Across 915 date-blinded papers from 1991 to 2025, average scores fell from 7.6/10 to 5.8/10 as megajournals and template database studies expanded. Blinded self-audits of 238 papers by two senior authors -- and of this manuscript itself -- caught real statistical, control, and table errors in our own work. At four cents per paper, BARS offers a practical quality check for authors, journals, and readers (https://veg.github.io/BARS/).

scientific communication and education↗
bioRxiv2026

From Problems to Solutions: How Self-Questions Drive Strong Scientific Reasoning

Metacognition, or awareness and control of thinking, is essential for problem solving because it helps solvers select strategies for learning and decide when to enact them (planning), check their understanding in the moment (monitoring), and assess effectiveness of solutions and learning strategies (evaluating). Most studies that examine metacognition do so retrospectively, leaving a critical gap in how metacognition is used in-the-moment for problem solving. In this study, we utilized a think-aloud interview approach to capture and characterize the metacognitive skills that senior undergraduate life science students at three institution types in the United States used spontaneously while solving challenging biology problems. We found that the students (n = 39) displayed a wide variety and quantity of monitoring, some evaluating, and nearly no planning skills while creating a solution backed with high-quality reasoning. Students frequently used self-questions to monitor and evaluate their thinking. We found that self-questioning is a critical skill for generating solutions, but it only moves problem solving forward if the student asks and correctly answers the self-question out loud. This study illustrates how self-questioning and other metacognitive regulation skills provide links to bridge the gap between a student's prior knowledge and specific features of a challenging problem. Based on our student data, we conceptualized a model of metacognitive phases during problem solving with high-quality reasoning. Finally, we present a self-question scaffold to facilitate the proposed phases (planning, monitoring, reasoning, and evaluating) so educators can equip students with metacognitive and scientific reasoning tools for effective problem solving.

scientific communication and education↗
bioRxiv2026

Preprint solicitation as a natural experiment in scholarly publishing

Preprinting is a growing and increasingly recognized mechanism for scientific communication and productivity and a way to facilitate global access to science. The interplay of preprinting practices with formal peer-reviewed publication is an open question that is now tractable to targeted analysis. Here, we take advantage of nearly a decade of preprint solicitation at Proceedings B to address this question, which offers a quasi-experimental setting for comparing outcomes for solicited preprints and traditionally submitted manuscripts. We used submission records from 15,368 manuscripts from 2018-2024 to assess whether preprint solicitation affects acceptance rates, journal scope, author geographic diversity, and post-publication uptake. Solicited manuscripts were accepted at nearly twice the rate of traditional submissions and received more downloads and citations after publication. Submission topics were broadly similar between the two routes, though solicited manuscripts showed marginally greater subject diversity. Geographic disparities favoring the Global North persisted, but acceptance rates for solicited manuscripts converged across regions, narrowing the gap seen in traditional submissions. These findings extend earlier work on this initiative and indicate that editor-driven solicitation can identify high-quality preprints, broaden geographic representation, and increase research visibility, offering a replicable model for journals seeking to diversify authorship while maintaining editorial standards.

scientific communication and education↗