Word Salad CAPTCHA - Application and Evaluation of Synthesized Sentences
Yoshifumi Kamoshida, Hiroaki Kikuchi · 2012
Artificially synthesized sentences are used for malicious purposes such as unsolicited commercial junk submission to Web site. We study a problem to distinguish between natural and synthesized messages generated in Markov chains and show experimental results. Based on the difficulties of the problem, we consider a new application to CAPTCHA, a type of challenge-response test used in computing to ensure that the response is not generated by a computer. Based on the experimental results, we have clarified that the parameters of N = 1 (order of Markov model), n = 5 (natural sentences), m = 15 (synthesized sentences), and = 15 for threshold of acceptance are optimal in terms of accuracy and efficiency. Our proposed Captcha is practical in the sense that the FRR and FAR is 2% in average.