Communications of the ACM
AI Model Fundamentally Cracks Captchas
A new computer model can solve Completely Automated Public Turing Tests to Tell Computers and Humans Apart (CAPTCHAs).
Credit: milindri/Getty Images/iStockphoto
Researchers at the artificial intelligence company Vicarious say they have developed a computer model that can solve Completely Automated Public Turing Tests to Tell Computers and Humans Apart (CAPTCHAs).
Vicarious co-founder Dileep George says the model cracks a CAPTCHA's defenses by parsing the text the test presents more effectively than earlier deep-learning models and with less training.
George cites the model's use of a Recursive Cortical Network, which is better able to reason about what it is seeing with less training than previous models. He says the network's training entails constructing internal models of the letters it is exposed to, and when a new image is presented it attempts to explain it, trying to define all of the pixels of that new image in terms of the characters it has previously seen.
George notes the long-term objective of such experiments "is to build intelligence that works like the human brain. CAPTCHAs were just a natural test for us."
From National Public Radio
View Full Article
Abstracts Copyright © 2017 Information Inc., Bethesda, Maryland, USA
No entries found