Fake Video Call Detection via Simultaneous Audio Stream Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Emergency 911 dispatch centers face challenges in identifying fake video calls in real-time, which can be maliciously streamed to call-takers, necessitating a rapid and effective method to differentiate between genuine and fake video feeds.
Innovation Solution
A method involving simultaneous audio and video calls, where the audio streams from both channels are compared to determine if the difference exceeds a threshold, with warnings provided to the operator through visual or audible messages, and further verification actions taken to confirm the authenticity of the video stream.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If audio streams from separate channels are compared to identify fake video calls, then the reliability of emergency response is improved, but the device complexity increases
Solution Approach 1:
The system segments the verification process by separating video and audio channels, comparing audio streams from different sources to detect inconsistencies. This segmentation allows targeted fraud detection without requiring complete system redesign
Solution Approach 2:
The audio comparison mechanism serves multiple functions: it verifies caller identity, detects fake videos, and provides actionable intelligence to call-takers. This multi-functionality improves reliability without proportionally increasing complexity
2Speed
If real-time audio stream comparison is performed, then the speed of fake video detection is improved, but the use of energy increases
Solution Approach 1:
Audio streams are captured and prepared for comparison in advance during the video call setup phase. This preliminary action enables rapid real-time detection without requiring intensive processing during critical verification moments
Solution Approach 2:
The system performs partial audio comparison by focusing on key audio features and thresholds rather than analyzing every audio sample in detail. This approach achieves sufficient detection speed while managing energy consumption
3Measurement precision
If audio streams are compared from separate channels, then the measurement precision of fake video identification is improved, but the difficulty of detecting and measuring increases
Solution Approach 1:
The system uses audio streams as an intermediary element to verify video authenticity. By comparing audio from separate channels, the system achieves precise fake video detection without directly analyzing video content, reducing measurement difficulty
Data Source
AI summary
A method and apparatus for identifying a faked video is provided herein. During operation, when a video, or video call is received from a device, a simultaneous audio call is placed to the device (i.e., the video call and audio call take place simultaneously in time). The audio streams on both the video and audio call are compared, and a difference between the audio streams is identified. The video is deemed a potential fake if the difference between the audio streams is above a particular threshold.