Exposing Fake Images With Forensic Similarity Graphs
Open accessThe DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
In this paper, we propose new image forgery detection and localization algorithms by recasting these problems as graph-based community detection problems. To do this, we introduce a novel graph-based representation of an image, which we call the Forensic Similarity Graph, that captures key forensic relationships among regions in the image. In this representation, small image patches are represented by graph vertices with edges assigned according to the forensic similarity between patches. Localized tampering introduces unique structure into this graph, which aligns with a concept called “community structure” in graph-theory literature. In the Forensic Similarity Graph, communities correspond to the tampered and unaltered regions in the image. As a result, forgery detection is performed by identifying whether multiple communities exist, and forgery localization is performed by partitioning these communities. We present two community detection techniques, adapted from literature, to detect and localize image forgeries. We experimentally show that our proposed community detection methods outperform existing state-of-the-art forgery detection and localization methods, which do not capture such community structure.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
Finding community structure in very large networks
Clauset, A., Newman, M. E. J., & Moore, C. (2004) · Physical Review E · doi:10.1103/physreve.70.066111 · Cited by 7,390
Resolution limit in community detection
Fortunato, S., & Barthélemy, M. (2007) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0605965104 · Cited by 3,024 · cited 2×
“Modularity optimization methods are well known to have difficulty in detecting communities much smaller in scale to the size of the graph [56].”
BackgroundStatistical mechanics of community detection
Reichardt, J., & Bornholdt, S. (2006) · Physical Review E · doi:10.1103/physreve.74.016110 · Cited by 2,048
Media Forensics and DeepFakes: An Overview
Verdoliva, L. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.3002101 · Cited by 979 · cited 1×
“3001516 have been found to be very effective for detecting and localizing image forgeries [15].”
BackgroundNoiseprint: A CNN-Based Camera Model Fingerprint
Cozzolino, D., & Verdoliva, L. (2020) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2019.2916364 · Cited by 499 · cited 6×
“algorithm [27], the Noiseprint algorithm [29], and our proposed Spectral Clustering algorithm.”
BackgroundMethodInfluentialInformation Forensics: An Overview of the First Decade
Stamm, M. C., Wu, M., & Liu, K. J. R. (2013) · IEEE Access · doi:10.1109/access.2013.2260814 · Cited by 394
Self-citation
Cited by
Media Forensics and DeepFakes: An Overview
Verdoliva, L. (2020) · IEEE Journal of Selected Topics in Signal Processing · doi:10.1109/jstsp.2020.3002101 · Cited by 979
“This work has been recently extended in [161] introducing a graph-based representation that better captures the forensic relationships”
BackgroundLearning Self-Consistency for Deepfake Detection
Zhao, T., Xu, X., Xu, M., Ding, H., Xiong, Y., & Xia, W. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01475 · Cited by 383
“The concept of inconsistency has been studied in the image forensic literature [34], where similarity scores are computed among image patches [34, 33, 14, 32, 60, 2].”
BackgroundWhat Makes Fake Images Detectable? Understanding Properties that Generalize
Chai, L., Bau, D., Lim, S.-N., & Isola, P. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58574-7_7 · Cited by 357
She, H., Hu, Y., Liu, B., Li, J., & Li, C.-T. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3451356 · Cited by 24
“2) Calculation of the Adjacency Matrix A: We use A to represent edge weights, which can be measured by the pairwise similarity between nodes [19], [20], [47].”
Method
Metadata
- Authors
- Mayer, O., & Stamm, M. C.
- Venue
- IEEE Journal of Selected Topics in Signal Processing
- Published
- 2020-08
- Volume
- 14
- Issue
- 5
- Pages
- 1049-1064
- ISSN
- 1932-4553 (ISSN-L)
- 1941-0484
- OpenAlex
- W2993158829
- Cited by
- 65
- References
- 6
- FWCI
- 3.80
- Type
- journal article
- Language
- en
- Open access
- green
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Exposing Fake Images With Forensic Similarity Graphs. https://app.cochat.ai/papers/10.1109/jstsp.2020.3001516
- The paper
- Mayer, O., & Stamm, M. C. (2020). Exposing Fake Images With Forensic Similarity Graphs. IEEE Journal of Selected Topics in Signal Processing. https://doi.org/10.1109/jstsp.2020.3001516
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.