Endpoint

1/25/2018
01:04 PM
100%
0%

New Voice MFA Tool Uses Machine Learning

Pindrop claims its new multi-factor authentication solution that uses the "Deep Voice" engine could save call centers up to $1 per call.

Voice security company Pindrop today announced the release of Deep Voice, a new voice biometrics engine that uses deep neural network machine learning technology, and the release of Pindrop Passport, a new multi-factor authentication product that is powered by the Deep Voice engine.

According to Pindrop, the Deep Voice engine can recognize a repeat caller regardless of whether there is background noise, whether they are making only short utterances, and whether they're speaking to an interactive voice response system, or a human call center agent. The engine uses whitelisting, blacklisting and anomaly detection. The individual's voice is analyzed every time they call, thereby strengthening the credential with every call.

The Pindrop Passport product combines Deep Voice, device authentication, and behavior analytics to create a passive multi-factor authentication solution that call centers can use to confirm callers' identity - instead of requesting personal information that might have been exposed in a data breach.  

Pindrop claims that Passport could reduce call handle times by up to 55 seconds and call center operations by up to $1 per call, as well as reduce fraud. 

Read more information here.

Dark Reading's Quick Hits delivers a brief synopsis and summary of the significance of breaking news events. For more information from the original source of the news item, please follow the link provided in this article. View Full Bio

Comment  | 
Print  | 
More Insights
Comments
Newest First  |  Oldest First  |  Threaded View
Register for Dark Reading Newsletters
White Papers
Video
Cartoon Contest
Current Issue
The Year in Security 2018
This Dark Reading Tech Digest explores the biggest news stories of 2018 that shaped the cybersecurity landscape.
Flash Poll
How Enterprises Are Attacking the Cybersecurity Problem
How Enterprises Are Attacking the Cybersecurity Problem
Data breach fears and the need to comply with regulations such as GDPR are two major drivers increased spending on security products and technologies. But other factors are contributing to the trend as well. Find out more about how enterprises are attacking the cybersecurity problem by reading our report today.
Twitter Feed
Dark Reading - Bug Report
Bug Report
Enterprise Vulnerabilities
From DHS/US-CERT's National Vulnerability Database
CVE-2018-6345
PUBLISHED: 2019-01-15
The function number_format is vulnerable to a heap overflow issue when its second argument ($dec_points) is excessively large. The internal implementation of the function will cause a string to be created with an invalid length, which can then interact poorly with other functions. This affects all s...
CVE-2018-7603
PUBLISHED: 2019-01-15
In Drupal's 3rd party module search auto complete prior to versions 7.x-4.8 there is a Cross Site Scripting vulnerability. This Search Autocomplete module enables you to autocomplete textfield using data from your website (nodes, comments, etc.). The module doesn't sufficiently filter user-entered t...
CVE-2019-3554
PUBLISHED: 2019-01-15
Wangle's AcceptRoutingHandler incorrectly casts a socket when accepting a TLS 1.3 connection, leading to a potential denial of service attack against systems accepting such connections. This affects versions of Wangle prior to v2019.01.14.00
CVE-2019-3557
PUBLISHED: 2019-01-15
The implementations of streams for bz2 and php://output improperly implemented their readImpl functions, returning -1 consistently. This behavior caused some stream functions, such as stream_get_line, to trigger an out-of-bounds read when operating on such malformed streams. The implementations were...
CVE-2019-0030
PUBLISHED: 2019-01-15
Juniper ATP uses DES and a hardcoded salt for password hashing, allowing for trivial de-hashing of the password file contents. This issue affects Juniper ATP 5.0 versions prior to 5.0.3.