TMCnews Featured Article

These days, there is more information being stored and shared by everyone all over the world. In addition, thanks to smartphones, tablets and a variety of other mobile devices, this information becomes accessible in so many different ways. Unfortunately, one thing that we have always seen is the fact that as more information becomes available the more creative hackers become in attempting to get ahold of it.

Over the past 12 months, we have seen more corporations that are considered to be giants in the business, getting hacked with tens of thousands of accounts being accessed. As a result, this has forced security firms to come up with more creative ways of keeping this information secure.

You would be hard-pressed to find a financial institution that is not constantly on the vigil, monitoring its accounts with fraud detection systems. As already mentioned, hackers and fraudsters are intelligent. If you remove the group of people that get hold of credit card information and quickly charge thousands of dollars’ worth of purchases out of the equation, you are left with the smart group that mimics normal usage, which means that it takes longer to realize that it is happening.

Biometrics has generally been a reliable method of security. Fingerprints and retinal information are unique, but they only work when you are physically present. Voice has emerged as a viable authentication method, because just like a fingerprint or iris, voice is unique to the individual. What sets voice apart as a preferred authentication method for online transactions is its ability to partner with the telephone to deliver extremely accurate remote authentication.

A voice biometric is a numerical representation of the sound, pattern, and rhythm of an individual’s voice. A voice biometric, or voice print, is as unique to an individual as a palm or fingerprint. Any application that employs a voice channel for authenticity during the out-of-band session is able to add voice biometric authentication to the process for even higher levels of authentication and security.

In a commentary by Wesley Wilhelm in InformationWeek’s Bank Systems & Technology section, he feels that by integrating voice biometric data into the process, it is possible to help improve fraud detection rates. This is done by adding a comparison of the voice used to initiate the fraud scheme or the fraud transactions with the legacy transaction analysis. Additionally, voice biometric analysis can assist with the post-fraud transaction verification processes, so calls to fraudsters who confirm their fraudulent activity as "legitimate" are detected.

One of the examples that Wilhelm uses is fraudulent wire transfers. I mentioned above how smart these people are; fraudsters are known to falsely generate wire transfer requests that are only slightly different than previous legitimate wire transfer requests. His feeling is that phone-initiated wire transfers should also include analysis of the voice requesting the wire.

Clearly there are a lot of situations where voice biometrics can be used to verify a user’s identity, such as requests for password resets, change of address, card reissues, check orders and wire transfer requests. It does seem that financial institutions are taking a serious look at this form of security. About one quarter of institutions that took part of an Aite Group survey indicated that they have pilot programs already place, with another 40 percent saying that the plan is to have voice biometrics set up within the next two years.

Biometrics has been a very successful security measure, but I do have one concern with respect to voice technology. My voice has been known to go down an octave or two when I have a really bad head cold. Does that mean that I would not have access to my accounts?

The fact of the matter is that we are seeing major developments in voice over LTE (News - Alert) (VoLTE), which is changing the way that some corporations are conducting business. Voice technology has come a very long way in a short amount of time. With that in mind, it is clear to see why Wilhelm feels that there should be little argument that it is time to enhance existing transaction detection systems by integrating voice biometric data analysis.