Identity Verification Injection Detection Using IMU-Video Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing digital identity verification systems are vulnerable to injection attacks, where an attacker aligns a mobile device camera with a display device to recapture and modify a video stream, bypassing conventional verification methods.
Innovation Solution
Utilizing inertial data from a mobile device's IMU in conjunction with video or image frames to detect micromovements or instructed movements, correlating these with the captured images to identify potential injection attacks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional identity verification methods are used, then the verification process is simple and user-friendly, but the system is vulnerable to injection attacks
Solution Approach 1:
The patent combines multiple data sources (video frames, still images, and inertial sensor data) into a unified verification process. The inertial data from the mobile device is merged with the visual capture data to create a multi-dimensional verification system that detects injection attacks by analyzing inconsistencies between expected and actual device movements.
Solution Approach 2:
The inertial measurement unit (IMU) data serves as an intermediary verification layer between the user and the identity verification system. By introducing this intermediate data source that tracks actual device movement, the system can detect when a device is being used to recapture display output without the user's physical movement matching the recorded video movements.
2Measurement precision
If inertial data and video frames are correlated to detect injection attacks, then detection accuracy improves, but processing complexity increases
Solution Approach 1:
The system performs preliminary correlation between inertial data and video frames during the identity verification process itself, rather than as a separate post-processing step. The inertial measurements are captured concurrently with video frame acquisition, allowing the system to establish movement patterns in advance and detect inconsistencies during the verification workflow.
Solution Approach 2:
The mobile device's camera and inertial sensors serve multiple functions: the camera captures both the user's face and the identification document, while the inertial sensors track device movement for both verification purposes and injection attack detection. This multi-functional approach consolidates what could be separate systems into a unified verification process.
Data Source
AI summary
Systems and methods for detecting an injection attack during a digital identity verification session are provided. The techniques include obtaining video frames and/or still image frames acquired using a camera of a mobile device, the video frames and/or the still image frames including images of a user and/or an identification document, and obtaining inertial data acquired using an inertial measurement unit (IMU) of the mobile device during the digital identity verification session. The techniques also include determining, using the video frames and/or the still image frames and the inertial data, whether the digital identity verification session is subject to the injection attack.