A Study on Broker-Assisted Blockchain Trust Chains for Provenance and Integrity Verification of Generative Media Using Watermarking, Semantic Fingerprinting, and C2PA
Open accessThe DOI matches its Crossref record; 23 of the 30 references it cites were found in a registry or an index, and 2 are not checked yet; 7 of the 17 sources its claims cite were checked for support.
Abstract
This research proposes a trust chain architecture that treats authenticity verification as an evidence registration and validation workflow rather than a single-signal decision.
Verified 2026-11-19 · 2 references not checked yet
Overview
CoChat Summary
TL;DR
The paper proposes a broker-assisted trust chain architecture that seals media with robust watermarking, embedding-based semantic fingerprints, and C2PA-compatible provenance manifests, storing sealed media off-chain via IPFS and anchoring compact evidence on an EVM ledger. On a COCO 2017 validation subset (N = 200), retrieval achieved Recall@1 = 0.9988 and Recall@5/10 = 1.000 under JPEG compression, resizing, and center cropping, while a representative registration transaction consumed 25,380 gas.
Key findings
- Retrieval was near-perfect on the COCO 2017 validation subset (N = 200): overall Recall@1 = 0.9988, Recall@5 = 1.0000, Recall@10 = 1.0000 under JPEG compression (Q = 50 and Q = 80), 0.5× bicubic resizing, and 10% center cropping. Per-transformation Recall@1 was 100.0% for JPEG Q = 50, 100.0% for JPEG Q = 80, 99.5% for resize, and 100.0% for center crop.
- On-chain anchoring overhead was low in the EVM proof-of-concept: a representative registration transaction consumed 25,380 gas for fixed-size compact evidence fields (CID hash, semantic fingerprint evidence hash, provenance manifest hash, timestamp; broker address as transaction sender). Annualized fee estimates ranged from 0.001506 ETH / $0.64 in 2020 to 0.000097 ETH / $0.31 in 2025, and 0.00000173 ETH / $0.0035 in March 2026.
- The architecture separates off-chain storage (IPFS content identifier), off-chain FAISS similarity search, and on-chain compact evidence; verification uses similarity search to retrieve candidates, then validates ledger inclusion and broker signatures, with optional watermark detection and sealed-media retrieval, issuing signed verdicts such as Verified, Derived, Unverified, and Suspected Tampered.
- The threat model treats watermarking as a complementary signal rather than a standalone guarantee; provenance metadata can be stripped, and ledger anchoring plus multi-field consistency checks are used to mitigate tampering, watermark degradation/removal, watermark copy/transfer, adversarial embedding manipulation, and semantic hash collision attempts.
Methods
- Design: a broker-assisted trust chain workflow with registration (watermark embedding, semantic fingerprint extraction, C2PA-compatible manifest generation, IPFS storage, ledger commitment) and verification (candidate retrieval, ledger record validation, signature checks, optional watermark detection/sealed-media retrieval, signed report issuance).
- Data and retrieval evaluation: COCO 2017 validation subset, N = 200 randomly sampled images with a fixed random seed; transformed queries used JPEG compression at Q = 50 and Q = 80, resizing to 0.5× with bicubic interpolation, and center cropping with 10% area reduction. Semantic fingerprinting used a pretrained CLIP image encoder (ViT-B/32) to extract L2-normalized embeddings; FAISS was used for nearest-neighbor retrieval; performance was reported as Recall@k.
- Ledger evaluation: an EVM-based proof-of-concept using a local Anvil testbed and a minimal EvidenceRegistry smart contract; each registration anchored fixed-size evidence fields including a CID hash (bytes32), semantic fingerprint evidence hash (bytes32), provenance manifest hash (bytes32), and timestamp (uint64), with per-registration overhead measured as gasUsed.
Limitations
- The paper states that the retrieval evaluation is conducted on a moderate-scale subset and under moderate transformations; stronger distortions such as rotation, heavy noise, adversarial perturbations, and more severe cropping may reduce similarity and should be evaluated further.
- The paper states that broker compromise or collusion is not fully prevented by design; the architecture aims to make broker-issued claims auditable through signatures and immutable record inclusion. It also notes that similarity-index configurations introduce accuracy-latency tradeoffs that should be characterized for large-scale deployments.
- Evident from the text: the evaluation does not benchmark specific watermarking algorithms or watermark robustness, and it measures retrieval performance plus per-transaction gas rather than full end-to-end overhead across sealing, storage, retrieval, verification, and IPFS workflows. The retrieval experiment uses COCO 2017 images, not generative media specifically, although the paper targets generative media provenance.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures





Verification
Claims the paper makes
5 Valid · 1 Not valid · 5 Not checked · 58 Own results and interpretations
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“Nevertheless, provenance metadata can be removed or altered unless it is bound to a tamper-evident mechanism that prevents undetected modification [4,5].”
§ A Study on Broker-Assisted Blockchain Trust Chains for Provenance and Integrity Verification of Generative Media Using Watermarking, Semantic Fingerprinting, and C2PA > 1. Introduction
What the sources say
- Not checked — no full text of the sourcecites [4] Igonor, O.S., Amin, M.B., and Garg, S. (2025). The Application of Blockchain Technology in the Field of Digital Forensics: A Literature Review. Blockchains, 3. source
- Supportedcites [5] Farhan, M., Butt, U., Bin Sulaiman, R., and Alraja, M. (2025). Self-Sovereign Identities and Content Provenance: VeriTrust—A Blockchain-Based Framework for Fake News Detection. Future Internet, 17. source
Section 2.5.5 says metadata-based provenance has limited trust guarantees in adversarial settings and describes cryptographic anchoring as a tamper-evident remedy. Section 4.4.2 describes signing metadata into a provenance record and committing its Merkle root on-chain; the Threat 5 discussion also acknowledges that off-chain provenance records can be lost or removed. Together, these passages support the paraphrase. (LLM, conf=0.88)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“In our prototype, a representative registration transaction consumed 25,380 gas for anchoring the compact evidence fields, demonstrating that minimal on-chain evidence recording can be performed with low ledger-side overhead while leaving large media objects off-chain.”
§ A Study on Broker-Assisted Blockchain Trust Chains for Provenance and Integrity Verification of Generative Media Using Watermarking, Semantic Fingerprinting, and C2PA > 5. Experimental Evaluation
boostedSingle case- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We evaluate the retrieval stage on a COCO 2017 validation subset (N = 200) under representative post-processing transformations (JPEG compression, resizing, and center cropping), and observe near-perfect candidate identification performance with Recall@1 = 0.9988 and Recall@5/10 = 1.000.”
§ A Study on Broker-Assisted Blockchain Trust Chains for Provenance and Integrity Verification of Generative Media Using Watermarking, Semantic Fingerprinting, and C2PA > Abstract
plainn = 200- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We evaluate the retrieval stage on a COCO 2017 validation subset (N = 200) under representative post-processing transformations (JPEG compression, resizing, and center cropping), and observe near-perfect candidate identification performance with Recall@1 = 0.9988 and Recall@5/10 = 1.000.”
§ A Study on Broker-Assisted Blockchain Trust Chains for Provenance and Integrity Verification of Generative Media Using Watermarking, Semantic Fingerprinting, and C2PA > Abstract
plainn = 200- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We also implement an EVM-based proof-of-concept for on-chain anchoring and report low ledger-side overhead for a representative registration transaction (gasUsed = 25,380) when recording fixed-size compact evidence fields.”
§ A Study on Broker-Assisted Blockchain Trust Chains for Provenance and Integrity Verification of Generative Media Using Watermarking, Semantic Fingerprinting, and C2PA > Abstract
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
22 more claims
Create a free account to see all 69 claims and to verify the 3 references still open.
- Probably not a substantial claim. 27
- It may state two separate claims as one. 27
Citations
Cites
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460
Learning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293
Billion-scale similarity search with GPUs
Johnson, J., Douze, M., & Jegou, H. (2021) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2019.2921572 · Cited by 4,228
Salakhutdinov, R., & Hinton, G. (2009) · International Journal of Approximate Reasoning · doi:10.1016/j.ijar.2008.11.006 · Cited by 1,246
Deepfake Media Forensics: Status and Future Challenges
Amerini, I., Barni, M., Battiato, S., Bestagini, P., Boato, G., Bruni, V., Caldelli, R., De Natale, F., De Nicola, R., Guarnera, L., et al. (2025) · Journal of Imaging · doi:10.3390/jimaging11030073 · Cited by 113
Blockchain-Based Multimedia Content Protection: Review and Open Challenges
Qureshi, A., & Megías Jiménez, D. (2020) · Applied Sciences · doi:10.3390/app11010001 · Cited by 91
Visual Content Privacy Protection: A Survey
Zhao, R., Zhang, Y., Wang, T., Wen, W., Xiang, Y., & Cao, X. (2024) · ACM Computing Surveys · doi:10.1145/3708501 · Cited by 89
Challenges of implementing ChatGPT on education: Systematic literature review
García-López, I. M., González González, C. S., Ramírez-Montoya, M.-S., & Molina-Espinosa, J.-M. (2025) · International Journal of Educational Research Open · doi:10.1016/j.ijedro.2024.100401 · Cited by 75
Sangeeta, N., & Nam, S. Y. (2023) · Electronics · doi:10.3390/electronics12071545 · Cited by 58
Social Image Security with Encryption and Watermarking in Hybrid Domains
Ye, C., Tan, S., Wang, J., Shi, L., Zuo, Q., & Feng, W. (2025) · Entropy · doi:10.3390/e27030276 · Cited by 49
Generative AI, copyright and the AI Act
Quintais, J. P. (2025) · Computer law & security review · doi:10.1016/j.clsr.2025.106107 · Cited by 44
The Application of Blockchain Technology in the Field of Digital Forensics: A Literature Review
Igonor, O. S., Amin, M. B., & Garg, S. (2025) · Blockchains · doi:10.3390/blockchains3010005 · Cited by 44
A Watermarking Protocol Based on Blockchain
Frattolillo, F. (2020) · Applied Sciences · doi:10.3390/app10217746 · Cited by 32
Корченко, О. Г., Tereikovskyi, I. A., Зюбина, Р., Tereikovska, L., Korystin, O. Y., Tereikovskyi, O., & Karpinskyi, V. (2025) · Applied Sciences · doi:10.3390/app15052553 · Cited by 19
Pedersen, K. T., Pepke, L., Stærmose, T., Papaioannou, M., Choudhary, G., & Dragoni, N. (2025) · Journal of Cybersecurity and Privacy · doi:10.3390/jcp5020018 · Cited by 15
A Dual-Branch Fusion Model for Deepfake Detection Using Video Frames and Microexpression Features
Petmezas, G., Vanian, V., Rufete, M. P., Almaloglou, E. E. I., & Zarpalas, D. (2025) · Journal of Imaging · doi:10.3390/jimaging11070231 · Cited by 8
Blockchain and Cloud to Overcome the Problems of Buyer and Seller Watermarking Protocols
Frattolillo, F. (2021) · Applied Sciences · doi:10.3390/app112412028 · Cited by 8
Farhan, M., Butt, U., Sulaiman, R. B., & Alraja, M. (2025) · Future Internet · doi:10.3390/fi17100448 · Cited by 7
Robust digital image watermarking using DWT, DFT and quality based average
Fullea, E., & Mart�nez, J. M. (2001) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/500141.500220 · Cited by 5
Data Organisation for Efficient Pattern Retrieval: Indexing, Storage, and Access Structures
Koukaras, P., & Tjortjis, C. (2025) · Big Data and Cognitive Computing · doi:10.3390/bdcc9100258 · Cited by 3
Document-Image Perceptual Hashing for Content Authentication
Situ, X., Liu, T., Yao, H., Qin, C., & Zhang, X. (2025) · IEEE Transactions on Big Data · doi:10.1109/tbdata.2025.3596854 · Cited by 2
P-HNSW: Crash-Consistent HNSW for Vector Databases on Persistent Memory
Lee, H., Park, T., Na, Y., & Kim, W.-H. (2025) · Applied Sciences · doi:10.3390/app151910554 · Cited by 1
A Robust Image Watermarking Scheme via Two-Stage Training and Differentiable JPEG Compression
Deng, H., Chen, F., Gan, P., Liao, R., & Yan, X. (2025) · Electronics · doi:10.3390/electronics14224510 · Cited by 1
Fullea, E., and Martínez Sánchez, J.M. (October, January 30). Robust Digital Image Watermarking Using DWT, DFT and Quality Based Average. Proceedings of the 9th ACM International Conference on Multimedia (MULTIMEDIA ′01), Ottawa, ON, Canada.
(n.d.)
UnresolvedCoalition for Content Provenance and Authenticity (C2PA) (2026, February 27). Content Credentials: C2PA Technical Specification, Version 2.3. Available online: https://spec.c2pa.org/specifications/specifications/2.3/specs/C2PA_Specification.html.
(n.d.)
Unresolved(2026, February 27). IPFS Docs. IPFS Documentation. Available online: https://docs.ipfs.tech.
(n.d.)
UnresolvedRadford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., and Clark, J. (2021, January 18–24). Learning Transferable Visual Models from Natural Language Supervision. Proceedings of the 38th International Conference on Machine Learning (ICML), PMLR 13
(n.d.)
UnresolvedCoinLedger (2026, March 28). Ethereum Transaction Fees and Gas Prices: Trends and Insights [2020–2025]. Available online: https://coinledger.io/research/ethereum-transaction-fees-and-gas-prices-trends-and-insights.
(n.d.)
UnresolvedWhiteBIT Blog (2026, March 28). Ethereum Price History: 2015–2026. Available online: https://blog.whitebit.com/en/ethereum-price-history/.
(n.d.)
UnresolvedEtherscan (2026, March 28). Ethereum Gas Tracker. Available online: https://etherscan.io/gastracker.
(n.d.)
Unresolved
Metadata
- Authors
- Yang, C., & Kim, M.
- Affiliations
- Mokpo National University (KR)
- Corresponding author
- Kim, Minchul
- ORCID
- Kim, Minchul
- Venue
- Applied Sciences
- Publisher
- MDPI AG
- Published
- 2026-03-31
- Volume
- 16
- Issue
- 7
- Pages
- 3391
- ISSN
- 2076-3417 (ISSN-L)
- OpenAlex
- W7147460381
- Semantic Scholar
- a89638ab24ea95da12a5bf0a44d64b9612120925
- Cited by
- 0
- References
- 28
- FWCI
- 0.00
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Applied Sciences (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Ministry of Education (2026-RISE-14-001)
- Topics
- Physical Sciences › Computer Science › Information Systems › Blockchain Technology Applications and Security
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Steganography and Watermarking Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Digital Media Forensic Detection
- Keywords
- blockchain anchoring, C2PA, provenance metadata, content-addressed storage, FAISS similarity search, candidate retrieval
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
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
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.