Marinus Awarded SBIR to Develop Adaptive Decoding of Text: Deobfuscating Text to Find Trafficking Victims

Pittsburgh, PA — Marinus Analytics has been awarded a National Science Foundation (NSF) Phase I Small Business Innovation Research (SBIR) for a project to develop new algorithms to enable predictive decoding of obfuscated text.

With the advent of the Internet, sex traffickers have been constantly innovating new ways to throw law enforcement agents off of their trail.  Particularly, perpetrators obfuscate—or attempt to disguise—the text used in ads that advertise their victims to veil pieces of information that would be useful to law enforcement, such as phone numbers and names.  These criminals can easily substitute Unicode characters into their ads, symbols which humans (their customers) can easily read, but computers cannot easily interpret for automated search or deeper analysis.  This leaves valuable evidence unrecognized, hindering law enforcement agents’ ability to track and catch traffickers.

There is no existing solution that can comprehensively and accurately decode the obfuscated information.  Such a flexible and adaptive solution is necessary in a world where criminal tactics are constantly changing and evolving.

Marinus’s solution will apply machine learning methods to train a model to predict the appropriate Latin character translation most likely to be represented by alternative symbols, essentially allowing for automatic and predictive decoding of obfuscated text.  Production of this unique set of algorithms will solve this problem adaptively, empowering law enforcement to stay ahead of criminal tactics as they evolve.

“This project has the potential to accelerate law enforcement agents’ ability to quickly and effectively track perpetrators, putting detectives ahead of the curve in their response to trafficking cases,” said Marinus CEO Emily Kennedy. “It also will have important application for other domains such as responses to spam and phishing schemes, which are increasingly popular in this Internet age.”

Marinus Analytics LLC is a women-owned spin-off company from the Auton Lab at Carnegie Mellon University, which produces and deploys data mining applications with social impact.  Marinus provides innovative technology based on the latest advancements in computer science to leverage big data to catch traffickers and rescue victims.

Media Contact:  Emily Kennedy, (866) 945-2803