AI & Fraud Detection Technology
Industry-leading protection against altered or tampered digital media
The Attestiv Platform is built on our patented AI technology to authenticate, validate, and protect the integrity of important digital media and data.
Our technology takes any digital media (including photos, videos, documents, sensor data, telemetry data, etc.) that is captured by Attestiv apps and APIs or imported from any external source to identify if it has been altered or tampered with.
We forensically scan each item to detect anomalies giving it a tamper score. We optionally store a fingerprint on a blockchain (distributed ledger) where it cannot be changed, enabling validation at any point in the future. We offer additional analysis to help automate and simplify processing of digital media, including text extraction and object recognition.
Our Process
Intake via app or API
Analysis and tamper detection
Validation & Reporting
Automation
(optional)
Details ↓
Intake via app or API
Details ↓
Real-time analysis & tamper detection
Details ↓
Validation & Reporting
Details ↓
Automation
Tamper Scoring System
Every image that gets analyzed by our system is given a score ranging between 1 to 100. Items scoring lower on the spectrum are considered to be trustworthy and need no further review. For document analysis the overall Tamper Score is either 0 or 100 where 0 means that the document is unaltered and 100 means that the document is altered.
We also group and analyze related images into an Analysis Report that summarizes and calls out areas needing review.
Find out more about our tamper scoring and reporting capabilities >
Our Image AI models explained
Images
Many editing tools leave traces in an image’s metadata. Additionally, bad actors may directly edit this data in an attempt to cover their tracks. This model searches through the image metadata for signs of this kind of tampering.
Documents
The metadata model looks for indicators of tampering in the scanned document’s EXIF data. Many editing tools will leave traces in the metadata, and in addition, fraudsters may edit this data directly to cover up their tracks.
Images
The provenance model matches images to the software in which they were saved, possibly after editing. If we trace the image back to an editing tool, like Photoshop, we can feel justified in being a little suspicious of that image.
Documents
The provenance model matches the scanned document to the software used to save the edits. If the scanned document can be traced back to an editing tool, then it indicates that the scanned document has been manipulated in some way.
Images only
The photo of photo model identifies photos of other photos or screens (television, computer monitors, etc.)
Images & Documents
The integrity model finds evidence of tampering in the image file itself. This includes checks such as mismatched file extensions and corrupted contents.
Images only
The quality model identifies photos that are exceptionally blurry or noisy.
Images only
The reverse search model performs a reverse image search against a wide range of websites.
Documents Only
This model highlights any text alterations it can find in the document using its deep-learning algorithms. It calculates a graded score based on the model’s confidence in its findings.
Features
Tamper-proof photos & videos
As data is captured from cameras or imported from digital media libraries, Attestiv captures metadata from the digital media and stores a unique “fingerprint” in an encrypted, tamper-proof blockchain distributed ledger.
Patented technology
Attestiv makes extensive use of AI algorithms to perform image categorization, text extraction, and authentication. Attestiv can even authenticate versions of an original photo or video that have been saved in different resolutions or formats.
Multiple authenticity levels
Attestiv verifies authenticity throughout the digital media file’s lifecycle and chain of custody. From Authenticated capture, to Imported, Scanned, Endorsed, or Altered.
Secure, evidence-grade proof
Because fingerprints are stored in a blockchain to ensure authentication, your data cannot be compromised. Traditional chain of custody protocols are no longer needed as digital media can be securely vaulted or shared with trusted parties. Regardless, Attestiv can identify changes or alterations, even eliminating insider threats.
Enterprise-ready
Attestiv is designed to meet enterprise security and compliance requirements, offering a storage agnostic architecture allowing secure storage of data virtually anywhere, ledger-agnostic architecture compatible with a choice of public or private distributed ledgers and enterprise ACLs that operate seamlessly with your existing user management.
Optimized User Experience
Whether your goal is to streamline workflows to save time and money or retain your existing branded front-end without altering familiar interfaces, Attestiv solutions will meet your user experience goals while you modernize the handling, tracking and validation of digital media files.
Our process
Capture or import
Capture or import digital media files like images, video, documents or data from mobile devices, cameras, drones, surveillance systems, or legacy digital media libraries through the Attestiv mobile or web app or APIs. Learn more about our Products.
Fingerprinting to the blockchain
Attestiv uses the media data to create a secure fingerprint. This fingerprint becomes a unique representation of the digital media asset, similar to human fingerprint and can identify future changes or alterations. Attestiv puts the fingerprint into a blockchain (which is tamper-proof). The digital media associated with the fingerprint does not have to be stored with the fingerprint and are generally vaulted separately meaning that you can keep them private and prove authenticity at any time in the future using Attestiv as a privacy silo.
Validation
Patented real-time verification informs viewers of the digital media whether it is authentic, imported, unknown or altered.
Real-time media analysis and tamper detection
Attestiv uses AI to detect photo or video anomalies and/or fraud attempts by using a forensic scan resulting in an aggregate tamper score. This scan includes metadata, provenance, photo of photo, image integrity, image quality, and a reverse search scoring of each piece of media.
Deep scan pixel-level image analysis
Attestiv allows for the deep scanning of images, with different sensitivity levels, to locate and isolate signs of manipulation or transplantation which are displayed via a heat map overlay.
Automation
Attestiv provides document analysis to read and process text within documents eliminating manual entry and also recognizes objects within images and videos.
Features
Tamper-proof photos & videos
As data is captured from cameras or imported from digital media libraries, Attestiv captures metadata from the digital media and stores a unique “fingerprint” in an encrypted, tamper-proof blockchain distributed ledger.
Patented technology
Attestiv makes extensive use of AI algorithms to perform image categorization, text extraction, and authentication. Attestiv can even authenticate versions of an original photo or video that have been saved in different resolutions or formats.
Multiple authenticity levels
Attestiv verifies authenticity throughout the digital media file’s lifecycle and chain of custody. From Authenticated capture, to Imported, Scanned, Endorsed, or Altered.
Secure, evidence-grade proof
Because fingerprints are stored in a blockchain to ensure authentication, your data cannot be compromised. Traditional chain of custody protocols are no longer needed as digital media can be securely vaulted or shared with trusted parties. Regardless, Attestiv can identify changes or alterations, even eliminating insider threats.
Enterprise-ready
Attestiv is designed to meet enterprise security and compliance requirements, offering a storage agnostic architecture allowing secure storage of data virtually anywhere, ledger-agnostic architecture compatible with a choice of public or private distributed ledgers and enterprise ACLs that operate seamlessly with your existing user management.
Optimized User Experience
Whether your goal is to streamline workflows to save time and money or retain your existing branded front-end without altering familiar interfaces, Attestiv solutions will meet your user experience goals while you modernize the handling, tracking and validation of digital media files.
Demo Videos
Industry Standards
Technology FAQs
- Do you require users to manually upload photos individually or do you accept large batches of photos?
We never require our customers to use the dashboard UI. It's more efficient to do an API integration for high photo volume.
- What is the difference between the analysis methods that Attestiv tests against?
Each of the models analyzes a different aspect of the media.
Metadata will look for any metadata anomalies that may indicate editing or tampering.
Provenance looks for traces left behind in the file by many photo editors.
Integrity evaluates whether the file structure is valid.
Photo of photo looks at whether the image may be a photo of a screen.
Quality determines if the file has potentially been modified to hide detail by lowering the quality.
Reverse Search looks for matches of the image on the internet potentially indicating the image is not original and has been downloaded. - Can you extract the original data from a fingerprint?
No, the fingerprint is a unique cryptographic representation of the media data and metadata.
- Do I need to store the media data on an Attestiv database?
No, the data can be kept in the user’s network. The fingerprint can be generated via APIs on the user’s network. Attestiv only manages the fingerprints that are stored on the blockchain.
- How does fingerprinting work?
A fingerprint is a unique signature that represents the contents of a digital asset. Attestiv distributes a library so that customers can generate fingerprints of their assets at the source. These fingerprints are sent to the Attestiv platform, where they are collected and written to an immutable blockchain. At any point, you can regenerate and compare the fingerprints of your assets to the original versions. If a file has been altered, the fingerprint will no longer match.
- What type of ledger do you use?
Attestiv has a ledger agnostic architecture that plugs into virtually any ledger. We support default public ledgers for customers who do not have specific ledger requirements. Contact us for details.
- Does Attestiv store my data?
Attestiv offers the option to store your data on secure cloud storage, but can also store the data on existing enterprise storage, without affecting regulatory compliance, security and disaster recovery requirements for organizations.
- Does any personal data get stored on the distributed ledger?
There is no need for any personal data to be stored on the ledger. Some applications may store non-identifiable context metadata for media files.
- Do you have technology that the forensic photo industry doesn't have?
Our combination real-time approach is unique because it includes fingerprinting, triage and deep scan which doesn’t exist elsewhere. We have the best solution on the market.
Attestiv Products, Solutions & Technology
Scalable. Secure. Compliant.
From the Blog
Interview with eChannelNEWS: Identifying Deepfakes
Nicos Vekiarides discusses the dramatic rise in deepfakes as a significant cyber threat with eChannelNews
Attestiv Joins NVIDIA Inception
Today Attestiv joined NVIDIA Inception, a program to help supercharge our AI-based products.
Deepfakes Scams Hit the WorkPlace
Wondering where else deepfake scams might pop up? How about coming to a workplace near you?
