Amazon Rekognition helps Marinus Analytics fight human trafficking

visual.jpg

Marinus Analytics provides law enforcement with tools, founded in artificial intelligence, to turn big data into actionable intelligence. The Marinus flagship software, Traffic Jam, is a suite of tools for use by law enforcement agencies on sex trafficking investigations.  Traffic Jam began as research by CEO Emily Kennedy at the Carnegie Mellon University Robotics Institute in 2011.  In 2014, Ms. Kennedy and her team founded the social innovation company, Marinus Analytics, to bring research and technology development solutions to make big data useful to law enforcement over the long term. Traffic Jam makes use of the huge amount of data online to proactively find victims, target criminals, and identify transnational criminal networks. These are a complex and evolving issues: “I am inspired by the impact we’ve seen thus far in the human trafficking space. Daily, we empower local, state, and federal law enforcement across the United States and Canada to rescue hundreds of victims and apprehend those who exploit them,” Kennedy says.

Now with Traffic Jam’s FaceSearch, powered by Amazon Rekognition, investigators are able to take effective action by searching through millions of records in seconds to find victims.

Recently, Marinus Analytics added facial recognition to the Traffic Jam platform using the Amazon Rekognition AI service. Marinus is the first group to effectively turn facial recognition technology against the vast, clandestine networks of human traffickers that prey upon our most vulnerable citizens. In the first few days following the release of Traffic Jam’s FaceSearch, law enforcement agents made multiple successful identifications of minors being sold online for sex. In one case, detectives identified the missing victim by searching her social media photos in FaceSearch. A positive match was quickly made and law enforcement was provided with the critical information to locate and rescue the victim.

Law enforcement needs sophisticated tools to foster victim-oriented policing in the age of the Internet. Law enforcement knew that runaway children are among the most likely to be trafficked. Before using Amazon Rekognition, their only recourse was to manually sift through online data to try to find them; this was time-intensive or not possible.  Now with Traffic Jam’s FaceSearch, powered by Amazon Rekognition, investigators are able to take effective action by searching through millions of records in seconds to find victims. They can use a photo of a missing child, a social media photo, or a photo from a social worker, and quickly determine whether a potential victim has been advertised online for commercial sex.

In one case, detectives identified the missing victim by searching her social media photos in FaceSearch. A positive match was quickly made and law enforcement was provided with the critical information to locate and rescue the victim.

Marinus Analytics has indexed over one and a half million faces in FaceSearch since its inception. The company uses a suite of AWS resources—in addition to Amazon Rekognition—to operate the Traffic Jam platform. Cara Jones, Chief Operating Officer, comments “In our engineering approach, we remain lean and cutting-edge through the use of AWS’s cloud infrastructure, intuitive administrative interfaces, and access to deep learning-based AI services , such as Amazon Rekognition. Facial Recognition was a long sought after feature by our users. AWS has allowed our startup to have a major impact in supporting law enforcement and in turn, helping victims of these crimes.”

There is interest among law enforcement to apply this tool more systematically and automatically, and in conjunction with other data sources, to proactively uncover human trafficking.  FaceSearch and future innovations by Marinus will help uncover this hidden crime in our communities, rescue victims, and bring their exploiters to justice. Marinus Analytics will continue to innovate using AWS services to ensure widespread social impact.