Risk
7/3/2008
03:17 PM
Connect Directly
Google+
LinkedIn
Twitter
RSS
E-Mail
50%
50%

IBM Develops Audio Masking Technology To Protect Call Center Recordings

Using speech analytics, the technology identifies and masks credit card numbers and other sensitive information in audio recordings.

Researchers at IBM's India Research Laboratory on Thursday said that they've developed a new data-masking technology to protect private information captured in call centers.

In a phone interview, J.R. Rao, senior manager of the secure software and services group at IBM's Thomas J. Watson Research Center in Yorktown Heights, N.Y., said that while theft of private information from call center recordings hasn't been a major issue, IBM wants "to proactively address a potential threat that can be used in an attack vector in call centers."

"This is a very important piece of technology because IBM takes security and privacy concerns of its customers very seriously, and it's key to maintaining customer trust," said Rao. He stressed the role that IBM Research is playing in bringing innovation to IBM's services business, a synergy often overlooked.

For IBM services clients with call centers, this technology should help ensure compliance with data security rules. "This is a technology that can be used to mask sensitive data and promote compliance with the numerous privacy and security laws that exist," said Rao.

Using speech analytics, the technology identifies sensitive information in audio recordings, such as credit card numbers, and masks it so that the data is only accessible to authorized people. With the help of metadata, the technology also masks sensitive information captured in recordings of call center computer screens, which are often associated with audio recordings.

Rao said the technology has been piloted in some call centers, but that IBM is not yet sure if whether it will be offered as a service or a shrink-wrapped product.

Comment  | 
Print  | 
More Insights
Register for Dark Reading Newsletters
White Papers
Cartoon
Current Issue
Flash Poll
Video
Slideshows
Twitter Feed
Dark Reading - Bug Report
Bug Report
Enterprise Vulnerabilities
From DHS/US-CERT's National Vulnerability Database
CVE-2014-2027
Published: 2015-03-31
eGroupware before 1.8.006.20140217 allows remote attackers to conduct PHP object injection attacks, delete arbitrary files, and possibly execute arbitrary code via the (1) addr_fields or (2) trans parameter to addressbook/csv_import.php, (3) cal_fields or (4) trans parameter to calendar/csv_import.p...

CVE-2014-2830
Published: 2015-03-31
Stack-based buffer overflow in cifskey.c or cifscreds.c in cifs-utils before 6.4, as used in pam_cifscreds, allows remote attackers to have unspecified impact via unknown vectors.

CVE-2014-7876
Published: 2015-03-31
Unspecified vulnerability in HP Integrated Lights-Out (iLO) firmware 2 before 2.27 and 4 before 2.03 and iLO Chassis Management (CM) firmware before 1.30 allows remote attackers to gain privileges, execute arbitrary code, or cause a denial of service via unknown vectors.

CVE-2014-9462
Published: 2015-03-31
The _validaterepo function in sshpeer in Mercurial before 3.2.4 allows remote attackers to execute arbitrary commands via a crafted repository name in a clone command.

CVE-2014-9706
Published: 2015-03-31
The build_index_from_tree function in index.py in Dulwich before 0.9.9 allows remote attackers to execute arbitrary code via a commit with a directory path starting with .git/, which is not properly handled when checking out a working tree.

Dark Reading Radio
Archived Dark Reading Radio
Good hackers--aka security researchers--are worried about the possible legal and professional ramifications of President Obama's new proposed crackdown on cyber criminals.