Combating Human Trafficking with Deep Multimodal Models

TL;DR

This paper introduces a new multimodal deep learning approach using text and image data to automatically detect human trafficking advertisements, supported by a large annotated dataset.

Contribution

It presents Trafficking-10k, a novel dataset, and the Human Trafficking Deep Network (HTDN), a deep multimodal model for trafficking ad detection.

Findings

High accuracy in detecting trafficking ads

Effective use of multimodal data improves detection

First large-scale dataset for this task

Abstract

Human trafficking is a global epidemic affecting millions of people across the planet. Sex trafficking, the dominant form of human trafficking, has seen a significant rise mostly due to the abundance of escort websites, where human traffickers can openly advertise among at-will escort advertisements. In this paper, we take a major step in the automatic detection of advertisements suspected to pertain to human trafficking. We present a novel dataset called Trafficking-10k, with more than 10,000 advertisements annotated for this task. The dataset contains two sources of information per advertisement: text and images. For the accurate detection of trafficking advertisements, we designed and trained a deep multimodal model called the Human Trafficking Deep Network (HTDN).