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... (read more)

PDF Abstract PDF Abstract

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
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 captcha_v2 Own CNN - multilabel classification Accuracy (%) 90.102% # 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 used in the Paper