The DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.
Adversarial attacks on medical machine learning
Open accessAbstract
Emerging vulnerabilities demand new conversations
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Existing research has shown that even small, imperceptible variations in the input data might lead AI models into incorrect decisions.60”
From FUTURE-AI: international consensus guideline for trustworthy and deployable artificial intelligence in healthcare (2025) · cites this paper as [60]
The cited source says what the claim attributes to it.
In the citing paper
“changes to medical imaging that are invisible, or appear random, to the human eye may change the likelihood of the diagnostic output entirely55,56.”
From Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI extension (2020) · cites this paper as [56]
The cited source says what the claim attributes to it.
In the citing paper
“For example, changes to medical imaging that are invisible, or appear random, to the human eye may change the likelihood of the resultant diagnostic output entirely47,48.”
From Guidelines for clinical trial protocols for interventions involving artificial intelligence: the SPIRIT-AI extension (2020) · cites this paper as [48]
In the citing paper
“For example, Finlayson et al. [110] have shown in a recent publication that the system’s output can completely be changed so that it classifies a mole as malignant with 100% confidence by making a small change in how inputs are presented to the system [109].”
From Ethical and legal challenges of artificial intelligence-driven healthcare (2020) · cites this paper as [110]
In the citing paper
“There is always a relatively high risk of adversarial attacks on health data systems [155]”
From Operationalising ethics in artificial intelligence for healthcare: a framework for AI developers (2023) · cites this paper as [155]
In the citing paper
“Moreover, such attacks have been already realized on ML/DL-based medical systems [31].”
From Explainable, trustworthy, and ethical machine learning for healthcare: A survey (2022) · cites this paper as [31]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Opportunities and obstacles for deep learning in biology and medicine
Ching, T., Himmelstein, D. S., Beaulieu-Jones, B. K., Kalinin, A. A., Do, B. T., Way, G. P., Ferrero, E., Agapow, P.-M., Zietz, M., Hoffman, M. M., et al. (2018) · Journal of The Royal Society Interface · doi:10.1098/rsif.2017.0387 · Cited by 2,310
End-To-End Arguments In System Design
And, S. R., Saltzer, J. H., Reed, D. P., & Clark, D. D. (1984) · Cited by 2,130
Wild patterns: Ten years after the rise of adversarial machine learning
Biggio, B., & Roli, F. (2018) · Pattern Recognition · doi:10.1016/j.patcog.2018.07.023 · Cited by 1,563
Robustness May Be at Odds with AccuracyPreprint
Tsipras, D., Santurkar, S., Engstrom, L., Turner, A., & Mądry, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.12152 · Cited by 1,513
The Future of the Internet--And How to Stop It
Zittrain, J. L. (2008) · Digital Access to Scholarship at Harvard (DASH) (Harvard University) · Cited by 1,371
Self-citation(2017) · doi:10.48550/arxiv.1712.02779 · Cited by 300
Adversarial Attacks Against Medical Deep Learning SystemsPreprint
Finlayson, S. G., Chung, H. W., Kohane, I. S., & Beam, A. L. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1804.05296 · Cited by 289
Self-citationPhysician manipulation of reimbursement rules for patients: between a rock and a hard place.
Wynia, M. K., Cummins, D. S., VanGeest, J. B., & Wilson, I. B. (2000) · PubMed · doi:10.1001/jama.283.14.1858 · Cited by 238
Corruption: medicine's dirty open secret
Jain, A., Nundy, S., & Abbasi, K. A. (2014) · BMJ · doi:10.1136/bmj.g4184 · Cited by 69
Overbilling vs. Downcoding — The Battle between Physicians and Insurers
Kesselheim, A. S., & Brennan, T. A. (2005) · New England Journal of Medicine · doi:10.1056/nejmp058011 · Cited by 26
Reynolds, K., Muntner, P., & Fonseca, V. A. (2005) · Diabetes Care · doi:10.2337/diacare.28.7.1831 · Cited by 24
Comparison of Anesthesia Times and Billing Patterns by Anesthesia Practitioners
Sun, E. C., Dutton, R. P., & Jena, A. B. (2018) · JAMA Network Open · doi:10.1001/jamanetworkopen.2018.4288 · Cited by 11
Flagged first, then by citations
Research works printed but not linked: 4
- N. Dalvi ., in KDD '04: Proceedings of the 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (ACM, New York, 2004).
- J. Li S. Ji T. Du B. Li T. Wang arXiv:1812.05271 [cs.CR] (13 December 2018). · arXiv
- A. Jain, S. Nundy, K. Abbasi, BMJ 348, g4181 (2014).
- 10.1145/357401.357402 · DOI
Cited by
Sorted by citations
Key challenges for delivering clinical impact with artificial intelligence
Kelly, C. J., Karthikesalingam, A., Suleyman, M., Corrado, G., & King, D. (2019) · BMC Medicine · doi:10.1186/s12916-019-1426-2 · Cited by 3,136
Scientific discovery in the age of artificial intelligence.
Wang, H., Fu, T., Du, Y., Gao, W., Huang, K., Liu, Z., Chandak, P., Liu, S., Van Katwyk, P., Deac, A., et al. (2023) · Nature · doi:10.1038/s41586-023-06221-2 · Cited by 1,823
Liu, X., Cruz Rivera, S., Moher, D., Calvert, M. J., Denniston, A. K., The SPIRIT-AI and CONSORT-AI Working Group, SPIRIT-AI and CONSORT-AI Steering Group, Chan, A.-W., Darzi, A., Holmes, C., et al. (2020) · Nature Medicine · doi:10.1038/s41591-020-1034-x · Cited by 1,421
Self-citationTransformers in medical imaging: A survey
Shamshad, F., Khan, S., Zamir, S. W., Khan, M. H., Hayat, M., Khan, F. S., & Fu, H. (2023) · Medical Image Analysis · doi:10.1016/j.media.2023.102802 · Cited by 1,523
Ethical and legal challenges of artificial intelligence-driven healthcare
Gerke, S., Minssen, T., & Cohen, G. (2020) · Artificial Intelligence in Healthcare · doi:10.1016/b978-0-12-818438-7.00012-5 · Cited by 1,170
Metadata
- Authors
- Finlayson, S. G., Bowers, J. D., Ito, J., Zittrain, J. L., Beam, A. L., & Kohane, I. S.
- Affiliations
- Harvard University (US)
- MIT Media Lab (US)
- Venue
- Science
- Published
- 2019-03-22
- Volume
- 363
- Issue
- 6433
- Pages
- 1287-1289
- ISSN
- 0036-8075 (ISSN-L)
- 1095-9203
- PMC
- PMC7657648
- OpenAlex
- W2924551358
- Semantic Scholar
- e718828e8f776d9f80daa3f8e0af6895f5d34c44
- Cited by
- 1,088
- References
- 10
- Citations by year
- 2026: 162 · 2025: 155 · 2024: 123 · 2023: 153 · 2022: 178 · 2021: 166 · 2020: 107 · 2019: 43
- FWCI
- 56.32
- Type
- journal article
- Language
- en
- Open access
- green
- www.ncbi.nlm.nih.gov
- Locations
- Science (publishedVersion)
- PubMed (publishedVersion)
- PubMed Central (acceptedVersion)
- Digital Access to Scholarship at Harvard (DASH) (Harvard University) (submittedVersion)
- Funders
- National Institute of General Medical Sciences (T32GM007753)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Adversarial Robustness in Machine Learning
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Keywords
- adversarial attacks, machine learning in medicine, model vulnerability, robustness, clinical decision support, cybersecurity in healthcare
- MeSH terms
- Machine Learning, Fraud, Humans, Insurance Claim Review
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
