Research Article

A generative vision model that trains with high data efficiency and breaks text-based CAPTCHAs

See allHide authors and affiliations

Science  08 Dec 2017:
Vol. 358, Issue 6368, eaag2612
DOI: 10.1126/science.aag2612

You are currently viewing the abstract.

View Full Text

Log in to view the full text

Log in through your institution

Log in through your institution

Computer or human?

Proving that we are human is now part of many tasks that we do on the internet, such as creating an email account, voting in an online poll, or even downloading a scientific paper. One of the most popular tests is text-based CAPTCHA, where would-be users are asked to decipher letters that may be distorted, partially obscured, or shown against a busy background. This test is used because computers find it tricky, but (most) humans do not. George et al. developed a hierarchical model for computer vision that was able to solve CAPTCHAs with a high accuracy rate using comparatively little training data. The results suggest that moving away from text-based CAPTCHAs, as some online services have done, may be a good idea.

Science, this issue p. eaag2612

Structured Abstract

INTRODUCTION

Compositionality, generalization, and learning from a few examples are among the hallmarks of human intelligence. CAPTCHAs (Completely Automated Public Turing test to tell Computers and Humans Apart), images used by websites to block automated interactions, are examples of problems that are easy for people but difficult for computers. CAPTCHAs add clutter and crowd letters together to create a chicken-and-egg problem for algorithmic classifiers—the classifiers work well for characters that have been segmented out, but segmenting requires an understanding of the characters, which may be rendered in a combinatorial number of ways. CAPTCHAs also demonstrate human data efficiency: A recent deep-learning approach for parsing one specific CAPTCHA style required millions of labeled examples, whereas humans solve new styles without explicit training.

By drawing inspiration from systems neuroscience, we introduce recursive cortical network (RCN), a probabilistic generative model for vision in which message-passing–based inference handles recognition, segmentation, and reasoning in a unified manner. RCN learns with very little training data and fundamentally breaks the defense of modern text-based CAPTCHAs by generatively segmenting characters. In addition, RCN outperforms deep neural networks on a variety of benchmarks while being orders of magnitude more data-efficient.

RATIONALE

Modern deep neural networks resemble the feed-forward hierarchy of simple and complex cells in the neocortex. Neuroscience has postulated computational roles for lateral and feedback connections, segregated contour and surface representations, and border-ownership coding observed in the visual cortex, yet these features are not commonly used by deep neural nets. We hypothesized that systematically incorporating these findings into a new model could lead to higher data efficiency and generalization. Structured probabilistic models provide a natural framework for incorporating prior knowledge, and belief propagation (BP) is an inference algorithm that can match the cortical computational speed. The representational choices in RCN were determined by investigating the computational underpinnings of neuroscience data under the constraint that accurate inference should be possible using BP.

RESULTS

RCN was effective in breaking a wide variety of CAPTCHAs with very little training data and without using CAPTCHA-specific heuristics. By comparison, a convolutional neural network required a 50,000-fold larger training set and was less robust to perturbations to the input. Similar results are shown on one- and few-shot MNIST (modified National Institute of Standards and Technology handwritten digit data set) classification, where RCN was significantly more robust to clutter introduced during testing. As a generative model, RCN outperformed neural network models when tested on noisy and cluttered examples and generated realistic samples from one-shot training of handwritten characters. RCN also proved to be effective at an occlusion reasoning task that required identifying the precise relationships between characters at multiple points of overlap. On a standard benchmark for parsing text in natural scenes, RCN outperformed state-of-the-art deep-learning methods while requiring 300-fold less training data.

CONCLUSION

Our work demonstrates that structured probabilistic models that incorporate inductive biases from neuroscience can lead to robust, generalizable machine learning models that learn with high data efficiency. In addition, our model’s effectiveness in breaking text-based CAPTCHAs with very little training data suggests that websites should seek more robust mechanisms for detecting automated interactions.

Breaking CAPTCHAs using a generative vision model.

Text-based CAPTCHAs exploit the data efficiency and generative aspects of human vision to create a challenging task for machines. By handling recognition and segmentation in a unified way, our model fundamentally breaks the defense of text-based CAPTCHAs. Shown are the parses by our model for a variety of CAPTCHAs .

Abstract

Learning from a few examples and generalizing to markedly different situations are capabilities of human visual intelligence that are yet to be matched by leading machine learning models. By drawing inspiration from systems neuroscience, we introduce a probabilistic generative model for vision in which message-passing–based inference handles recognition, segmentation, and reasoning in a unified way. The model demonstrates excellent generalization and occlusion-reasoning capabilities and outperforms deep neural networks on a challenging scene text recognition benchmark while being 300-fold more data efficient. In addition, the model fundamentally breaks the defense of modern text-based CAPTCHAs (Completely Automated Public Turing test to tell Computers and Humans Apart) by generatively segmenting characters without CAPTCHA-specific heuristics. Our model emphasizes aspects such as data efficiency and compositionality that may be important in the path toward general artificial intelligence.

View Full Text