Artificial intelligence bid to halt human trafficking

| March 29, 2019 | 0 Comments

Since 2016, information technology (IT) experts from George Washington University in Washington DC, Temple University in Philadelphia, Pennsylvania, and Adobe Research in San Jose, California, have been using artificial intelligence to help rescue children caught up in sex trafficking rings around the world.
In early February 2019, the IT team told a conference in Hawaii how a Global Hotel Recognition Dataset (GHRD) would work.
For more than two years, its designers have been collecting photographs of 50,000 hotels around the world. Says lead researcher Abby Stylianou:
Recognising a hotel from an image of a hotel room is important for human trafficking investigations. Images directly link victims to places and can help verify where victims have been trafficked, and where their traffickers might move them or others in the future. Recognising the hotel from images is challenging because of low image quality, uncommon camera perspectives, large occlusions (often the victim), and the similarity of objects (e.g., furniture, art, bedding) across different hotel rooms.
To support efforts towards this hotel recognition task, we have curated a dataset of over one million annotated hotel room images from 50,000 hotels across the globe.
All of the gathered photos, says Stylianou, have been processed by a large artificial intelligence machine called a “deep
convolutional neural network” (DCNN), which is smart enough to learn a set of identifying filters or markers. It can identify, for example, which hotels use which headboards or lamps.
The powerful app, now called Hotels-50K, still needs some tweaking. Says Stylianou, “The first thing we have to do is erase the victim from the image [of the hotel room]. The reason is to protect the victim, so that their image isn’t going back and forth across the internet.”
As the number of people trapped in sexual slavery passed the 4.5 million mark in early 2019, some global hotel chains are educating their employees to look out for signs that someone may be being held against their will. Requests for frequent sheet changes and “do not disturb” signs that are never removed are suspicious markers, say police.
In early March 2019, A German court jailed four men convicted of founding and running a darknet forum for child pornography, with tens of thousands of members swapping illegal pictures and videos.

Category: Autumn 2019

About the Author ()

News posts added for Independent Education by Global Latitude DMA

Leave a Reply

Your email address will not be published. Required fields are marked *