Just as people's voices betray hints of the region they originate from, so, it turns out, do phone calls. Handsets, telephone exchanges, and other call-routing infrastructure imprint subtle and almost unique fingerprints onto the audio of any phone call, a phenomenon that security company Pindrop hopes to use to prevent fraudsters from using stolen credit cards over the phone.The Pindrop technology is interesting and creative and adds the "fourth factor" to authentication.
"We can identify whether a person is using a landline or cell phone, or when a call supposed to come from a mobile in Atlanta comes from a landline in Nigeria," says Vijay Balasubramaniyan, CEO and cofounder of Pindrop. The "secret" answers and words used to protect bank and other accounts are often easily compromised, particularly using data gleaned online, or through tactics like phishing. Spoofing a caller ID to match a victim's number when calling their bank has also become commonplace, says Balasubramaniyan.
The article also sheds a little bit of light on the challenges of telephone voice recognition. Everything that makes Pindrop possible makes designing voice recognition algorithms harder, because it's not just the background line noise that changes, the voice changes, too.
Perhaps something like Pindrop could be used to correct for the subtle shifts imposed by the voice network and to present a clean sample to the voice recognition algorithm.
