Digital Document Provenance Chain via Distributed Ledger Hashing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increasing sophistication of digital image and audio editing technologies, such as deepfake methods, makes it difficult to detect alterations in digital assets, leading to concerns like body dysmorphic disorders, deceptive advertising, and copyright infringement, and existing tools for analyzing changes in digital documents on distributed ledgers are inadequate for complex transactions and multiple versions.
Innovation Solution
A system that generates and utilizes a chain of provenance for digital documents by storing document state data, including digital fingerprints and edit logs, on a distributed ledger, allowing for the tracing and auditing of changes made to the documents through a unique identifier, enabling the identification of edits and their attribution.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If digital image and audio editing technologies are used to alter digital assets, then the visual appearance and speech can be modified, but the detectability of alterations becomes difficult
Solution Approach 1:
The system performs preliminary actions by generating cryptographic hashes of digital assets and storing them on a distributed ledger before alterations occur. This creates a baseline provenance record that enables future detection of changes, resolving the contradiction by establishing detectability mechanisms in advance rather than attempting to detect changes after sophisticated editing has been performed
Solution Approach 2:
The patent introduces an intermediary provenance tracking system that mediates between the digital asset and its alterations. This intermediary system uses cryptographic hashing and distributed ledger technology to create an independent verification layer that can detect changes without being affected by the sophistication of editing tools, thus resolving the detection difficulty while maintaining editing capability
2Ease of manufacture
If conventional image editing applications are used to modify digital images, then the visual appearance can be altered, but verification of unaltered copies becomes challenging
Solution Approach 1:
The patent replaces mechanical visual verification methods with cryptographic hash-based verification. Instead of relying on human observers to detect visual alterations, the system uses cryptographic hashing to create immutable digital fingerprints of the original assets, stored on a distributed ledger, enabling precise automated verification that is insensitive to the sophistication of editing applications
3Ease of manufacture
If deep learning methods are used to alter audio recordings, then speech can be modified, but the non-detectability of alterations gives rise to concerns
Solution Approach 1:
The system performs preliminary cryptographic hashing of audio recordings and stores the hashes on a distributed ledger before deep learning alterations occur. This creates a reliable baseline that enables future verification of audio authenticity, resolving the reliability concern by establishing a tamper-evident record in advance
Solution Approach 2:
The patent introduces an intermediary provenance system that mediates between the original audio and deep learning alterations. This intermediary uses cryptographic verification to maintain reliability independent of the audio manipulation capabilities, allowing detection of alterations while preserving the ability to edit audio using deep learning methods
Data Source
AI summary
Embodiments provide traceability of edits to a document, i.e., a verifiable and immutable provenance chain for the document. In particular, embodiments facilitate providing analytics services for a distributed ledger. In implementation, a unique identifier associated with a digital document can be received from a remote computing device. Based on the received unique identifier, it is determined that the distributed ledger includes a first transaction corresponding to a first transitioned state of the digital document and a second transaction corresponding to a second transitioned state of the digital document. Each transaction includes the unique identifier, a first fingerprint of the digital document generated at a first time of a transitioned state, and a second fingerprint of the digital document generated at a second time of a previously transitioned state. Thereafter, a provenance chain of the digital document including the first transaction followed by the second transaction is determined based on a determination that the second fingerprint of the second transaction corresponds to the first fingerprint of the first transaction.