Overview

Product video
Shufti Deepfake Detection for faces enables financial institutions to quantify how many historic KYC approvals involved AI generated or manipulated faces. The AMI is deployed inside the institutions own AWS account so biometric data remains inside existing security and compliance boundaries.
The engine examines previously approved selfie images from onboarding and authentication flows and flags known deepfake patterns, face swaps and other generative AI artefacts that pass basic ID checks. This gives MLROs, fraud leaders and technology teams a clear measure of deepfake exposure in the current customer base based on real historic data rather than synthetic tests.
The AMI operates as a batch audit layer. Institutions select the historic cohorts that matter most such as specific time windows, products or geographies and obtain a clear genuine or deepfake view for each face. The flexible pricing makes an initial deepfake audit a practical objective for the next risk committee or board cycle.
Highlights
- Multi-layered fraud defence: Deepfake detection plugs into Shufti's wider risk and verification stack, so synthetic faces are not evaluated in isolation.
- In-house proprietary tech: No reliance on third-party deepfake modules, ensuring transparency, adaptability, and control.
- Built for adversarial scenarios: Engineered to expose subtle generative artefacts even when synthetic faces look visually convincing to human reviewers.
Details
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
Pricing
Dimension | Description | Cost/month |
|---|---|---|
Verification | Number of Verification/Requests | $0.08 |
Vendor refund policy
Usage based charges are generally non refundable. If you believe you were charged due to a service defect (e.g., container unavailability), open a ticket within 7 days with timestamps and logs. Verified incidents may be credited or refunded at our discretion. Refunds are processed through AWS Marketplace per AWS refund procedures
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
64-bit (x86) Amazon Machine Image (AMI)
Amazon Machine Image (AMI)
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
Shufti Face Deepfake App
Additional details
Usage instructions
Before deploying the Shufti Face Deepfake Detection AMI, ensure you have an AWS account with permissions to launch EC2 instances and create IAM roles and instance profiles, an active subscription to the product in AWS Marketplace, and a network setup including a VPC, Subnet, and Security Group with HTTP (port 80) open. The recommended instance type is r7i.4xlarge or larger (Nitro Enclave support required).
To deploy, launch a new EC2 instance using the AMI and paste the provided Shufti initialization script in Advanced Details User Data. Provisioning typically takes about 25 minutes. After provisioning completes, open the EC2 Console, copy the Public IP of the instance, and access the application at: http://<EC2_PUBLIC_IP>:80.
Ensure the Security Group allows port 80, and if provisioning exceeds 25 minutes, review EC2 system logs or console output. For detailed deployment instructions and API usage, see the full Shufti user guide: https://developers.shuftipro.com/docs/marketplaces/aws/user-guide
Support
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.