PROJECT TITLE :

Using JPEG to Measure Image Continuity and Break Capy and Other Puzzle CAPTCHAs

ABSTRACT:

Human interactive proofs (HIPs) are a basic security live on the Web to avoid several types of automatic attacks. A selection of designs are proposed. Here, the authors target a new sort of HIP, based on a puzzle completion scheme that has been created to increase security and value: the Capy CAPTCHA (Fully Automated Public Turing test to tell Computers and Humans Apart). Analyzing its design, the authors find vital flaws and weaknesses, and propose an occasional-cost, facet-channel attack, using JPEG to measure the image's continuity. Their attack contains a sixty five % success rate. When analyzing experimental results, they extended their approach to alternative puzzle CAPTCHAs, breaking them at twenty % (KeyCAPTCHA) and 98 % (Garb) success ratios.