2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2019
DOI: 10.1109/cvprw.2019.00338
|View full text |Cite
|
Sign up to set email alerts
|

ARCHANGEL: Tamper-Proofing Video Archives Using Temporal Content Hashes on the Blockchain

Abstract: We present ARCHANGEL; a novel distributed ledger based system for assuring the long-term integrity of digital video archives. First, we describe a novel deep network architecture for computing compact temporal content hashes (TCHs) from audio-visual streams with durations of minutes or hours. Our TCHs are sensitive to accidental or malicious content modification (tampering) but invariant to the codec used to encode the video. This is necessary due to the curatorial requirement for archives to format shift vide… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
10
0
1

Year Published

2020
2020
2024
2024

Publication Types

Select...
5
4

Relationship

2
7

Authors

Journals

citations
Cited by 21 publications
(11 citation statements)
references
References 25 publications
0
10
0
1
Order By: Relevance
“…For this reason, many DLT implementations rely upon the distributed ledger to underpin the integrity of an otherwise mutable data store such as a cloud-based data lake (Franceschi et al, 2018). Trust in data is derived from transparency and nonrepudiation (evidenced, for example, by hashes or "fingerprints" of data) whilst accommodating its future redaction (Collomosse et al, 2018;Bui et al, 2019;Yang et al, 2020). This and other issues with contemporary DLT (principally, scalability) point to DLT, not as a storage technology for immutable data, but as a supportive technology to underwrite the integrity and promote trust in data.…”
Section: Issues Of Trust and Privacymentioning
confidence: 99%
“…For this reason, many DLT implementations rely upon the distributed ledger to underpin the integrity of an otherwise mutable data store such as a cloud-based data lake (Franceschi et al, 2018). Trust in data is derived from transparency and nonrepudiation (evidenced, for example, by hashes or "fingerprints" of data) whilst accommodating its future redaction (Collomosse et al, 2018;Bui et al, 2019;Yang et al, 2020). This and other issues with contemporary DLT (principally, scalability) point to DLT, not as a storage technology for immutable data, but as a supportive technology to underwrite the integrity and promote trust in data.…”
Section: Issues Of Trust and Privacymentioning
confidence: 99%
“…Bottleneck zt serves as the content hash and is compressed via PQ post-process (not shown). incarnation of ARCHANGEL described in Collomosse et al [47], [4] which utilised a proof-of-work (PoW) blockchain to store SHA-256 hashes of binary zip files containing academic research data. Also related, is the prior work of Gipp et al [49] where SHA-256 hashes specifically of video are stored in a PoW (Bitcoin) blockchain for evidencing car collision incidents.…”
Section: Related Workmentioning
confidence: 99%
“…The hash is computed over both the audio and the visual components of the video stream. We initially proposed an earlier version of our TCH scheme using a hybrid CNN-LSTM network in workshop paper [4]. In this extended paper we build on this approach to propose HAAEa hierarchical LSTM architecture that also incorporates a novel attention scheme.…”
Section: Introductionmentioning
confidence: 99%
“…Archangel. The TCH is stored on the blockchain while the algorithm and video are stored off-chain (Bui et al, 2019).…”
Section: Blockchain and Records Managementmentioning
confidence: 99%