Dartmouth professor’s “robust hashing” can spot terrorism videos automatically

An algorithm based on “robust hashing” of video images, developed by digital-image-forensics expert Hany Farid at Dartmouth, is being touted as a new way to limit the spread of violent recruitment videos online. Basically, once a video is identified by a human as a terrorism-recruitment video, the hashing makes it possible for it to be automatically recognized – even if edited, added to, or tweaked – and removed, thus solving this problem:

“As soon as you take one of these videos down, they get posted in 20 other places. You can play whack-a-mole, but you’ll never win,” said Farid, who heads the computer science department at Dartmouth.

Here’s the column.