Medical Image Tampering Detection: A New Dataset and Baseline
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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 growing use of highly synthetic data or images by generative AI, such as CorGAN, exacerbates the situation as it becomes increasingly challenging for human professionals to detect unfaithful data and outputs.
“The growing use of highly synthetic data or images by generative AI, such as CorGAN, exacerbates the situation as it becomes increasingly challenging for human professionals to detect unfaithful data and outputs [69].”
From Generative AI in medical practice: in-depth exploration of privacy and security challenges (2024) · cites this paper as [69]
Generative AI, such as GANs, has empowered hackers to generate or change the attributes or content of medical images with high visual realism, making the detection of tampered images extremely difficult.
“Furthermore, generative AI, such as GANs, has empowered hackers to generate or change the attributes or content of medical images with high visual realism, making the detection of tampered images extremely difficult [69].”
From Generative AI in medical practice: in-depth exploration of privacy and security challenges (2024) · cites this paper as [69]
Cites
Detection of GAN-Generated Fake Images over Social Networks
Marra, F., Gragnaniello, D., Cozzolino, D., & Verdoliva, L. (2018) · 2018 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR) · doi:10.1109/mipr.2018.00084 · Cited by 399 · see citing works
Deep learning enables reduced gadolinium dose for contrast-enhanced brain MRI
Gong, E., Pauly, J. M., Wintermark, M., & Zaharchuk, G. (2018) · Journal of Magnetic Resonance Imaging · doi:10.1002/jmri.25970 · Cited by 351 · cited 1× · see citing works
“While machine learning and artificial intelligence technologies are developed for many online applications of medical imaging analysis [11, 22], data security (i.”
Background
Flagged first, then by citations
Cited by
Sorted by citations
Generative AI in medical practice: in-depth exploration of privacy and security challenges
Chen, Y., & Esmaeilzadeh, P. (2024) · Journal of Medical Internet Research · doi:10.2196/53008 · Cited by 353 · see citing works
“…and moving it to another area), classical inpainting tampering (ie, patching a missing area with tampered image slices), deep inpainting tampering (ie, similar to classical inpainting tampering but using highly realistic image slides generated by GANs), sharpening, blurring, and resampling [69].”
Influential
- Authors
- Reichman, B., Jing, L., Akin, O., & Tian, Y.
- Affiliations
- City University of New York (US)
- Corresponding author
- Tian, Yingli
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer International Publishing
- Published
- 2021
- Pages
- 266-277
- ISSN
- 0302-9743 (ISSN-L)
- 1611-3349
- OpenAlex
- W3133303693
- Cited by
- 13
- References
- 2
- Citations by year
- 2026: 1 · 2025: 3 · 2024: 4 · 2023: 4 · 2021: 1
- FWCI
- 0.74
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- Lecture notes in computer science (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Steganography and Watermarking Techniques
- Physical Sciences › Mathematics › Statistics and Probability › Benford’s Law and Fraud Detection
- Keywords
- computed tomography, deep learning, healthcare data security
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
