ISSN (Online) : 2456 - 0774

Email : ijasret@gmail.com

ISSN (Online) 2456 - 0774

SURVEY PAPER ON DESIGNING IMAGE BASED CAPTCHA USINGMACHINE LEARNING

Abstract

Abstract: - The capacity of programmers to infiltrate computer systems using computer attack programs and bots prompted the development of Captchas, or Completely Automated Public Turing Tests to Tell Computers and Humans Apart. The Text Captcha is the most well-known Captcha conspire, given its simplicity of development and ease of use. However, the hackers and programmers have reduced the expected security of Captchas, leaving websites open to attack. Text Captchas are still broadly utilized on the grounds that it is trusted that the attack speeds are moderate, regularly two to five seconds for each picture, and this isn't viewed as a basic risk. In this paper, a novel image-based Captcha known as Style Area Captcha (SACaptcha) is proposed, which depends on semantic data understanding, pixel-level segmentation and deep learning techniques. Experimental demonstrated that text Captchas are no longer secure, the proposed SACaptcha shows the development of image-based Captchas using deep learning techniques for increasing the security purpose.Keywords - Captcha, text-based, security, deep learning, Convolutional neural network, image-based.

Full Text PDF

IMPORTANT DATES 

Submit paper at ijasret@gmail.com

Paper Submission Open For October 2024
UGC indexed in (Old UGC) 2017
Last date for paper submission 30th October, 2024
Deadline Submit Paper any time
Publication of Paper Within 15-30 Days after completing all the formalities
Publication Fees  Rs.6000 (UG student)
Publication Fees  Rs.8000 (PG student)