Voice Liveness Verification via Dynamic Challenge-Response
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Voice-based authentication systems are vulnerable to replay attacks, where an imposter presents a pre-recorded audio sample of an enrolled user's passphrase, fooling the system into believing the user is present at the point of authentication.
Innovation Solution
Implementing voice-based liveness verification by presenting a series of randomly selected liveness passphrases to the user during authentication, which are previously enrolled, and verifying that the user's utterances match the enrolled samples, thereby determining if the user is a live subject.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a single static passphrase is used for voice authentication, then the ease of operation is improved, but the reliability is worsened due to vulnerability to replay attacks
Solution Approach 1:
The system transitions from a static passphrase to a dynamic challenge-response mechanism where multiple passphrases are randomly selected during authentication. This dynamic approach prevents replay attacks while maintaining user convenience, as the user simply responds to random prompts without needing to memorize multiple fixed passphrases.
Solution Approach 2:
The system pre-enrolls multiple passphrases for each user during the enrollment phase. These passphrases are stored and later randomly selected during authentication challenges. This preliminary preparation enables the system to present unpredictable challenges that cannot be replayed, thereby enhancing security while keeping the authentication process simple for the user.
2Reliability
If multiple liveness passphrases are enrolled and randomly selected during authentication, then the reliability is improved by preventing replay attacks, but the device complexity increases
Solution Approach 1:
The authentication system is segmented into distinct functional modules: an enrollment module for capturing and storing multiple passphrases, an authentication module for presenting random challenges, and a verification module for comparing responses. This modular segmentation manages complexity by organizing functions into separate, manageable components while achieving enhanced security through multi-passphrase verification.
Data Source
AI summary
Techniques for implementing voice-based liveness verification are provided. In one embodiment, a computing device can present a series of challenge prompts to a user being authenticated, where each challenge prompt corresponds to a request to utter a liveness passphrase that is randomly selected from a set of liveness passphrases that have been previously enrolled by an enrolled user of the computing device. The computing device can then receive utterances from the user in response to the series of challenge prompts and, if each utterance matches its corresponding enrolled liveness passphrase, can conclude that the user is a live subject.