PinDr0p - Voice-Routing Call Fingerprint System Fights 'Vishing'

Via The Register UK -

Security researchers in the States say they have developed a cunning new method of "fingerprinting" voice calls that could offer a route to trustworthy caller ID and a barrier against so-called "vishing" or voice phishing.

The tool is called PinDr0p, and works by analysing the various characteristic noise artifacts left in audio by the different types of voice network - cellular, VoIP etc. For instance, packet loss leaves tiny gaps in audio signals, too brief for the human ear to detect, but quite perceptible to the PinDr0p algorithms. Vishers and others wishing to avoid giving away the origin of a call will often route a call through multiple different network types.

[...]

According to the system's inventors, there's no way for vishers or other voicey villains to eliminate the traces a given system of call routing leaves in the audio eventually received at the other end.

“They’re not able to add the kind of noise we’re looking for to make them sound like somebody else,” says Patrick Traynor, GIT compsci prof. “There’s no way for a caller to reduce packet loss. There’s no way for them to say to the cellular network, ‘Make my sound quality better.’”

The PinDr0p analysis can't produce an IP address or geographical location for a given caller, but once it has a few calls via a given route, it can subsequently recognise further calls via the same route with a high degree of accuracy: 97.5 per cent following three calls and almost 100 per cent after five.

Naturally a visher can change routings easily, but even so PinDr0p can potentially reveal details that will reveal a given call as being false. A call which has passed through a Russian cell network and P2P VoIP is unlikely to really be from your high-street bank in the UK, for instance.

The GIT researchers hope to develop a database of different signatures which would let their system provide a geolocation as well as routing information in time.

[...]

The PinDr0p research was funded by the US National Science Foundation. There's a statement on it here.