Apr 10 2019
The U.S. Department of Homeland Security defines human trafficking as modern-day slavery that “involves the use of force, fraud, or coercion to obtain some type of labor or commercial sex act,” and this crime is notoriously challenging to prosecute.
“It is often misidentified as a single, isolated crime, like prostitution or a drug offense,” stated Dan Lopresti, professor and chair of the department of science and engineering at Lehigh University’s P.C. Rossin College of Engineering and Applied Science. “And unless you put together the pieces, you don’t realize there is a much bigger picture.”
A team of experts in artificial intelligence (AI), computational researchers, and other members of the technology community have collaborated with law enforcement officials, policy experts, survivors, and activists to help figure this out.
Imagine the techniques that Google and Facebook are using to make a profit—understanding people, the way they connect, what their interests are, what they might buy or the activities they engage in. We can apply those same techniques—data mining, text mining, what’s called graph mining—AI that’s being used for legitimate and really profitable purposes, to track these illicit behaviors.
Dan Lopresti, Professor and Chair, Department of Science and Engineering, P.C. Rossin College of Engineering and Applied Science, Lehigh University
Despite the fact that traffickers have recruited potential victims and advertised to customers using the Internet and social media platforms, according to Lopresti, the same networks offer opportunities for eliminating criminal activity.
Lopresti is a member of the Executive Committee of the Computing Research Association’s Computing Community Consortium (CCC) and has helped set up a two-day conference at the United Nations in February known as “Code 8.7: Using Computational Science and AI to End Modern Slavery.” The conference witnessed the gathering of top researchers, social scientists, policy makers, survivors, and representatives of the tech community to delve deep into the topic.
The name Code 8.7 refers to Target 8.7 of the United Nations’ Sustainable Development Goals, which aims at ending modern slavery, forced labor, and human trafficking by 2030, and the worst forms of child labor by 2025.
According to Lopresti, this is the right time to move further from our dependence on good—but fortuitous—observations to expose human trafficking crimes. He added that it is time to leverage technology to offer support to trained law enforcement in handling this complex issue.
Finding a solution to the problem of human trafficking is not just a technical one. It also involves social policy and political. As a researcher, if you don’t understand this, you could come up with a solution that you think is elegant mathematically but is totally irrelevant in the real world. So that’s why we wanted to be in the same room with the social scientists and the policy makers.
Dan Lopresti, Professor and Chair, Department of Science and Engineering, P.C. Rossin College of Engineering and Applied Science, Lehigh University
From the year 2015, Jennifer Gentile Long, a Lehigh graduate and chief executive officer of AEquitas—a resource that helps prosecutors who work on cases of gender-based violence and human trafficking—and Lopresti have joined hands on computer-science-based attempts to help AEquitas manage and exploit the enormous amount of text data in legal documents to support the work of the organization in helping prosecutors come up with stronger cases.
The conference was co-hosted with the United Nations University Centre for Policy Research, the Alan Turing Institute, Tech Against Trafficking, University of Nottingham Rights Lab, and Arizona State University Global Security Initiative and marks the start of the organizers’ plan to be a multiyear collaboration working over the issue.
It was amazing to see experts in all these fields come together and try to coordinate efforts so that people are working toward solutions, not working haphazardly. They are making a true impact on this crime—identifying victims at points where they are missed, providing opportunities to leave and find safety, identifying perpetrators, and looking at policy in a coordinated effort. And it’s so great to see Lehigh, in a way, sitting at the head of the table.
Jennifer Gentile Long, Graduate, Lehigh University; CEO, AEquitas
Human trafficking survivors shared their stories with attendees during the closing session of the conference.
“It reminded everyone,” stated Lopresti, “that even though we are talking about information, data, and policy, which all seem abstract, the data is real people. You can’t treat a problem like this abstractly.”
“Technology alone can’t solve the problem,” added Long, “but when we combine it with training efforts to develop highly skilled, trauma-informed investigators and prosecutors, we can enhance victim identification and safety.”
Mining the data for hidden evidence
Lopresti’s interests in the global discussion surrounding modern slavery follow from his study outside of the university on a local level, as part of his involvement with the Regional Intelligence and Investigation Center (RIIC) in Allentown, Pa.—a city with over 120,000 residents located near Bethlehem, where Lehigh University is located.
The RIIC was launched in 2013 and has “revolutionized” the manner in which area police departments “analyze and share collected data to solve crimes,” says James Martin, the Lehigh County District Attorney.
I had no idea in our own backyard this was happening. But the same reason that drives Amazon to build a big warehouse in this region of the country—accessibility to large populations—is why this region, known as the Lehigh Valley, is also a hub for human trafficking, drug trafficking, gangs, and some very serious criminal activity.
Dan Lopresti, Professor and Chair, Department of Science and Engineering, P.C. Rossin College of Engineering and Applied Science, Lehigh University
Lopresti, an expert in pattern recognition and document analysis, has collaborated with RIIC Director Julia Kocis, law enforcement officials, prosecutors, and other Rossin College computer science and engineering faculty members—Jeffrey D. Heflin, Sihong Xie, and Eric P.S. Baumer—to help solve the problems in turning enormous amounts of data, primarily from police incident reports, into something usable, in spite of restricted resources.
“If an expert sits down and reads enough of these, he or she will find a common thread—this person is related to this place, which is related to this activity, which is related to this other person,” he stated. “The trouble is, they’ve got millions of these reports and just don’t have enough time to read through them. We’re developing natural language techniques, text mining and data mining techniques that are oriented to processing lots of data to identify patterns of behavior that would reflect illegal activities related to human trafficking.”
Kocis presented their study at Code 8.7, reiterating the “wealth of evidence that’s evidence hiding within freeform text and unstructured data that AI techniques can help identify.” According to the office of the Lehigh County District Attorney, “Efficient access to this information will place law enforcement in a better position to help victims, investigate and prosecute traffickers and deter buyers.”