Detection of Malicious Video Modifications using Perceptual Video Hashing
Abstract
The perceptual video hashing (PVH) function produces fixed-length and a compact video fingerprint (or perceptual video hash) based on the perceptual contents of the video. This fingerprint can be used for detection of malicious video modifications or video tamper detection based on its perceptual contents, video authentication and video copyright protection. Here, the video fingerprint is extracted using the three-dimensional (3D) radial projection (RP) technique and the two-dimensional (2D) discrete cosine transform (DCT). The proposed algorithm is inspired from the following algorithms: video hashing based on 2D-RP of key frames and the video hashing based on 3D-RP technique. The performance of all the aforementioned algorithms are assessed using the receiver operating characteristics curves. The proposed algorithm perform better in the context of detecting malicious attacks.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Cited by
Sorted by citations
Perceptual Robust Hashing for Video Copy Detection with Unsupervised Learning
Zhao, G., Qin, C., Luo, X., Zhang, X., & Chang, C.-C. (2023) · Proceedings of the 2023 ACM Workshop on Information Hiding and Multimedia Security · doi:10.1145/3577163.3595110 · Cited by 1 · see citing works
“The technique of perceptual hashing [1] can map multimedia data into a short sequence, which is equivalent to the fingerprint of multimedia data, known as hash code, and can be used in the fields of copy detection [2], content authentication [3], tampering detection [4], etc.”
Method
- Authors
- Sandeep, R., & Bora, P. K.
- Affiliations
- Indian Institute of Technology Guwahati (IN)
- Venue
- 2020 5th International Conference on Computing, Communication and Security (ICCCS)
- Publisher
- IEEE
- Published
- 2020-10-14
- Pages
- 1-5
- OpenAlex
- W3113211004
- Cited by
- 7
- References
- 0
- Citations by year
- 2025: 1 · 2024: 2 · 2023: 3 · 2021: 1
- FWCI
- 0.31
- Type
- conference paper
- Language
- en
- Open access
- closed
- Licence
- Locations
- International Conference on Computing, Communication and Security (ICCCS) (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 › Computer Science › Computer Vision and Pattern Recognition › Chaos-based Image/Signal Encryption
- Keywords
- video tamper detection, video fingerprinting, discrete cosine transform, video authentication, video copyright protection, key frames
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
