.svg){kind=logo}
The following sections list every released version of Liveness Detection, newest first. Each section comes from the monthly OCP® Release Notes page named in its Released line.
Liveness Detection 7.3.0
Released: November 2026
|
US1 |
US2 |
EU1 |
|---|---|---|
|
— |
— |
— |
RA Detection model — v4.0.5
-
The current trend is to use bots to complete users' tasks. Such bots may use cheaper standard TTS (concatenative synthesis). In order to improve detection of these bots, we intend to enlarge our training set for liveness detection models with relevant data.
Security
-
Resolved security vulnerabilities
Liveness Detection 7.2.0
Released: October 2026
|
US1 |
US2 |
EU1 |
|---|---|---|
|
— |
— |
— |
RA Detection model — v4.0.4
-
Liveness detection training data is expanded with alphanumeric utterances, combining genuine samples from real calls with spoofed counterparts generated from them via VC-TTS.
Fixes
-
Model fails during stress tests
Liveness Detection 7.1.0
Released: September 2026
|
US1 |
US2 |
EU1 |
|---|---|---|
|
— |
— |
— |
RA Detection model - v4.0.3
-
Replayed genuine data labeled as spoofed removed from training
Liveness Detection 7.0.0
Released: September 2026
|
US1 |
US2 |
EU1 |
|---|---|---|
|
— |
— |
— |
RA Detection model - v4.0.2
-
Incorporated W2V-BERT 2.0 architecture into training scripts
-
Implemented training data augmentation into the liveness detection training pipeline
-
Added ArcticEcho data to the training corpus for liveness detection
-
Additional TTS data for liveness detection training
-
Implemented multi-head attentive statistics pooling for liveness detection models
Liveness Detection
-
The first 3 sec chunk without duplication
Fixes
-
Fixed zero-downtime feature
-
Changed normalization
Liveness Detection 6.1.1
Released: August 2026
|
US1 |
US2 |
EU1 |
|---|---|---|
|
— |
— |
— |
Improvements
-
Change the logic so that the first 3 sec of an audio chunk, which is duplicated, are not counted in the overall average score.
-
New calibration values for the model 3.1.0
Liveness Detection 6.1.0
Released: July 2026
|
US1 |
US2 |
EU1 |
|---|---|---|
|
— |
— |
— |
This release introduces version 3.1.0 of the RA Detection model, normalizes scoring logic for Liveness Detection, adds new deployment capabilities, and improves system security.
RA Detection model
-
Introduces version 3.1.0 of the RA Detection model.
-
Adds new data to the training set.
Liveness Detection
-
Normalizes output scores to the [0, 1] range.
-
Revises thresholding logic to align with the new score range.
-
Updates label selection to reflect the revised threshold.
Deployment
-
Adds support for zero-downtime deployments.
Security
-
Resolves security vulnerabilities.
Liveness Detection 6.0.1
Released: June 2026
|
US1 |
US2 |
EU1 |
|---|---|---|
|
— |
— |
— |
-
This release addresses high-severity vulnerabilities identified in third-party library dependencies. The affected libraries have been updated to remediate the findings and reduce exposure to potential security risks.
For more information go to Liveness Detection.
Liveness Detection 6.0.0
Released: May 2026
|
US1 |
US2 |
EU1 |
|---|---|---|
|
— |
— |
— |
New Features
-
Enhanced Liveness Detection Model Selection - The Liveness Detection service now supports an additional inference model alongside the existing on-premise model. Operators can direct liveness checks to either the local model or the new cloud-based inference engine, and configure the confidence threshold used to determine a live result, giving greater flexibility to tune accuracy for different deployment contexts.
Liveness Detection 5.2.2
Released: March 2026
|
US1 |
US2 |
EU1 |
|---|---|---|
|
— |
— |
— |
-
Core libraries and dependencies were updated to meet latest security standards. This routine maintenance mitigates potential vulnerabilities and improves overall system stability.
For more information, see Liveness Detection.
Liveness Detection 5.2.1
Released: March 2026
|
US1 |
US2 |
EU1 |
|---|---|---|
|
— |
— |
— |
-
Change in the Replay Attack Detection threshold that is expected to decrease the False Acceptance Rate (FAR).
For more information, see Liveness Detection.
Liveness Detection 5.2.0
Released: November 2025, January 2026
|
US1 |
US2 |
EU1 |
|---|---|---|
|
— |
— |
— |
For more information, see the Liveness Detection guide.
-
The Liveness Detection service has been migrated to ARM-based images
-
Security update to resolve Liveness Detection Service (OOD and RA) vulnerabilities detected by AWS Inspector.
-
Migrate to a modern high-performance dependency manager for faster builds and improved cross-platform support.
-
Liveness Detection service code optimization for enhanced security.
-
RA Detection service code optimization for better model performance.