Locally Authenticated Privacy-preserving Voice Input
release_zbxp6ioyybhwrhn2etezqnerem
by
Ranya Aloufi, Andreas Nautsch, Hamed Haddadi, David Boyle
2022
Abstract
Increasing use of our biometrics (e.g., fingerprints, faces, or voices) to
unlock access to and interact with online services raises concerns about the
trade-offs between convenience, privacy, and security. Service providers must
authenticate their users, although individuals may wish to maintain privacy and
limit the disclosure of sensitive attributes beyond the authentication step,
\eg~when interacting with Voice User Interfaces (VUIs). Preserving privacy
while performing authentication is challenging, particularly where adversaries
can use biometric data to train transformation tools (e.g.,`deepfaked' speech)
and use the faked output to defeat existing authentication systems. In this
paper, we take a step towards understanding security and privacy requirements
to establish the threat and defense boundaries. We introduce a secure, flexible
privacy-preserving system to capture and store an on-device fingerprint of the
users' raw signals (i.e., voice) for authentication instead of sending/sharing
the raw biometric signals. We then analyze this fingerprint using different
predictors, each evaluating its legitimacy from a different perspective (e.g.,
target identity claim, spoofing attempt, and liveness). We fuse multiple
predictors' decisions to make a final decision on whether the user input is
legitimate or not. Validating legitimate users yields an accuracy rate of
98.68% after cross-validation using our verification technique. The pipeline
runs in tens of milliseconds when tested on a CPU and a single-core ARM
processor, without specialized hardware.
In text/plain
format
Archived Files and Locations
application/pdf 2.4 MB
file_5oip2v2dwzga5dvn6c2mas3sdy
|
arxiv.org (repository) web.archive.org (webarchive) |
2205.14026v1
access all versions, variants, and formats of this works (eg, pre-prints)