Google Turns Antipiracy Tools Against Child Porn
Google has repurposed the high-tech digital fingerprinting technologies it uses to weed out infringing material from YouTube and turned it against those who trade in child pornography. The company has teamed up with the National Center for Missing and Exploited Children to test the technology.
04/15/08 2:45 PM PT
A handful of Google engineers has redesigned a set of video and image analysis tools to help find missing children and combat child pornography and abuse. Their effort is now being tested by the National Center for Missing and Exploited Children (NCMEC), and it stems from anti-piracy software Google developed for the company's YouTube division.
The software is designed for find patterns in images and video, and the NCMEC will likely use it to track down child predators and find and identify missing and abused children. Since its inception in 1984, the private, non-profit NCMEC has reported more than 570,000 child exploitation leads to law enforcement agencies and assisted with more than 140,900 missing child cases -- but the most important number is the 124,500 children who have been recovered.
Millions of Images
Working in cooperation with federal law enforcement agencies, analysts with NCMEC's Child Victim Identification Program (CVIP) have reviewed more than 13 million child pornography images and videos since 2002 -- and about five million of those were in the last year. It's an overwhelming process, NCMEC said.
"Criminals are using cutting edge technology to commit their crimes of child sexual exploitation, and in fighting to solve those crimes and keep children safe, we must do the same," noted Ernie Allen, president and CEO of NCMEC.
"That is why we are so grateful to Google for providing new tools that will enable the National Center to better serve law enforcement in battling exploitation and rescuing children," he added.
The Google technology lets NCMEC analysts more quickly and easily search NCMEC's systems to sort and identify files that contain images of child pornography victims, NCMEC says. The new video tools will also help streamline analysts' review of video snippets from files seized in child pornography cases.
Working With Law Enforcement
While the NCMEC isn't a government organization, it does work closely with government agencies, several of which have agents or officers working on site at the NCMEC where they can coordinate between NCMEC resources and the needs of local law enforcement agencies.
In child pornography and exploitation cases, defendants often try to argue in court that the pornographic images of children in question aren't real children, Michelle Collins, executive director of Exploited Children Services at the NCMEC, told TechNewsWorld. While the NCMEC doesn't maintain a victim database of identified children, the organization can provide information about which images contain children that law enforcement officers or agencies have already identified.
"We have an awful lot of information on children that we know law enforcement has found," Collins explained. "And it's one more piece of information that can help knock down the defense."
How It Works
Both Google and the NCMEC haven't revealed many details surrounding the new technology, which isn't surprising given the sensitive nature of law enforcement investigations into child pornography and abuse. However, Larry Magid, founder of SafeKids.com and an unpaid member of the NCMEC board of directors, posted a few examples on SafeKids.com that illustrate the power of Google's contribution.
"The software allows an analyst to highlight a pattern somewhere in an image. It could be a calendar on the wall, a logo on a T-shirt, a prominent tattoo or perhaps the pattern of the carpet. It then looks for that pattern in other images and when it finds a match or a likely match it presents those images to the analyst. In some cases it will analyze the entire image to look for matches or near matches," Magid wrote, noting that without the software, human analysts must depend on memory to catch similar or unique characteristics between images.
"Our analysts have been doing a tremendous job with their memory, but computers have much longer memories," Collins said, noting that while a human might not remember a pattern seen 4 million images ago, "the system should be still able to pick that up."
The team of Google engineers was led by Dr. Shumeet Baluja. Back in August of 2006, Google joined NCMEC's Technology Coalition Against Child Pornography, which, along with other tech industry companies, develops solutions that hinder predators' abilities to use the Internet to exploit children or traffic in child pornography.
As an offshoot of that program, Baluja realized the NCMEC could use a technology solution to sort through an ever-growing number of child pornography images, which are sent to the organization via the NCMEC CyberTipline.
Baluja recruited some fellow engineers, and throughout 2007, they used 20 percent of their workday to focus on the humanitarian effort. Google, in fact, has a company program that fosters such innovation by letting its engineers spend 20 percent of their time working on most any pet project they feel passionate about, whether it's for Google or for the greater good.
"You always hope that your work will eventually be used [to] do some good in the world," noted Baluja on the Official Google Blog.
"This was an amazing chance to make that hope real ..." he added.