Pindrop Security provides enterprise solutions that help prevent phone-based fraud. Its acoustical fingerprinting technology detects fraudulent calls and authenticates legitimate callers, helping customers eliminate financial losses and reduce operational costs. Pindrop Security’s breakthrough technology is the first of its kind to fingerprint individual phone calls, providing verification of caller provenance. Recently named one of the 10 Most Innovative Companies at the 2012 RSA conference and a Gartner “Cool Vendor” in Enterprise Unified Communications and Network Services for 2012, Pindrop Security’s solutions help companies feel more confident in the security of phone-based financial transactions.
Research Engineer
IBM
May 2010 - Aug 2010(4 months)
Analyzed techniques used by malicious entities, in Twitter, to disseminate dubious information while appearing legitimate. Identified features in their behavior, including their artificially created social network and interaction history, and create algorithms based on these features to distinguish them from regular users.
Software Engineer
Google
May 2008 - Aug 2008(4 months)
Research Engineer
IBM
May 2006 - Aug 2007(1 year 4 months)
Senior Software Engineer
Siemens
Jul 2003 - Jul 2005(2 years 1 month)
Software Engineer
Intel
Aug 2002 - Jul 2003(1 year)
Education
verified_user
0% verified
PhD, Computer Science
Georgia Institute of Technology
Jan 2005 - Jan 2011(6 years 1 month)
My graduate work focused on identifying features in communication systems to characterize wanted and unwanted interactions and encapsulate them as interaction credentials. In VoIP, we use call duration and direction to create these interaction credentials and combine them with social network theory and Eigentrust to help distinguish regular users from spammers. We also study how to privately propagate these credentials to address the introduction problem. Currently extending this work to mobile spam.
Bachelor of Engineering (B.E, Computer Science & Engineering
RV College of Engineering
Jan 1998 - Jan 2002(4 years 1 month)
Publications
verified_user
0% verified
I
SERvartuka: Dynamic Distribution of State to Improve SIP Server Scalability
IEEE Conference on Distributed Computing Systems ICDCS Jan
A
PinDr0p: Using Single-Ended Audio Features to Determine Call Provenance
ACM Conference on Computer and Communications Security CCS Oct
In this paper, we develop PinDr0p, a mechanism to assist users in determining call provenance — the source and the path taken by a call.