Embedded Blockchains: A Synthesis of Blockchains, Spread Spectrum Watermarking, Perceptual Hashing & Digital Signatures
This addresses the issue of media integrity verification for applications like forensics or content authentication, but it appears incremental as it combines existing techniques without a major breakthrough.
The paper tackles the problem of detecting manipulated audio and video by introducing an Embedded Blockchain scheme that synthesizes blockchains, spread spectrum watermarking, perceptual hashing, and digital signatures, resulting in a method to verify media integrity by traversing a unique blockchain for each recording and estimating manipulation levels if the chain is broken.
In this paper we introduce a scheme for detecting manipulated audio and video. The scheme is a synthesis of blockchains, encrypted spread spectrum watermarks, perceptual hashing and digital signatures, which we call an Embedded Blockchain. Within this scheme, we use the blockchain for its data structure of a cryptographically linked list, cryptographic hashing for absolute comparisons, perceptual hashing for flexible comparisons, digital signatures for proof of ownership, and encrypted spread spectrum watermarking to embed the blockchain into the background noise of the media. So each media recording has its own unique blockchain, with each block holding information describing the media segment. The problem of verifying the integrity of the media is recast to traversing the blockchain, block-by-block, and segment-by-segment of the media. If any chain is broken, the difference in the computed and extracted perceptual hash is used to estimate the level of manipulation.