Deceiving computers in Reverse Turing Test through Deep Learning

1 Jun 2020  ·  Jimut Bahan Pal ·

It is increasingly becoming difficult for human beings to work on their day to day life without going through the process of reverse Turing test, where the Computers tests the users to be humans or not. Almost every website and service providers today have the process of checking whether their website is being crawled or not by automated bots which could extract valuable information from their site. In the process the bots are getting more intelligent by the use of Deep Learning techniques to decipher those tests and gain unwanted automated access to data while create nuisance by posting spam. Humans spend a considerable amount of time almost every day when trying to decipher CAPTCHAs. The aim of this investigation is to check whether the use of a subset of commonly used CAPTCHAs, known as the text CAPTCHA is a reliable process for verifying their human customers. We mainly focused on the preprocessing step for every CAPTCHA which converts them in binary intensity and removes the confusion as much as possible and developed various models to correctly label as many CAPTCHAs as possible. We also suggested some ways to improve the process of verifying the humans which makes it easy for humans to solve the existing CAPTCHAs and difficult for bots to do the same.

PDF Abstract

Datasets


Results from the Paper


 Ranked #1 on CAPTCHA Detection on captcha_4_letter (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
CAPTCHA Detection captcha-1L Own CNN model - multilabel classification Accuracy 99.67% # 1
CAPTCHA Detection captcha_4_letter LSTM Multilabel Classification Acc 99.87 # 1
CAPTCHA Detection circle_captcha Alex Net with multilabel classification Accuracy (%) 99.99% # 1
CAPTCHA Detection CNN_c4l_16x16_550 Modified CIFAR-10 for Multilabel Classification Accuracy 99.91% # 1
CAPTCHA Detection faded Alex Net with multilabel classification Accuracy (%) 99.44% # 1
CAPTCHA Detection fish_eye Alex Net with multilabel classification 99.46% Accuracy # 1
CAPTCHA Detection JAM CAPTCHA k-NN ensemble Accuracy 99.53% # 1
CAPTCHA Detection mini_captcha Alex Net with multilabel classification Accuracy (%) 97.25% # 1
CAPTCHA Detection multicolor Alex Net with multilabel classification Accuracy (%) 95.69% # 1
CAPTCHA Detection railway_captcha Own CNN model Accuracy (%) 99.94% # 1
CAPTCHA Detection sphinx Alex Net with multilabel classification Accuracy (%) 99.62% # 1

Methods