Exploiting the human-machine gap in image recognition for designing CAPTCHAs

The multimedia research community has, for long, attempted to recognize generic images, make them searchable by content, annotate them, and associate them with linguistic indexes. In the course of these attempts, the limitations of state-of-the-art algorithms in mimicking human vision has become wellknown. In this paper, we explore the exploitation of this limitation for solving a security problem. While undistorted natural images have been shown to be algorithmically recognizable and searchable by content to moderate levels, controlled distortions of specific type and strength can potentially make machine recognition harder without affecting human recognition. This difference in recognizability makes it a promising candidate for automated Turing tests called CAPTCHAs which can differentiate humans and machines. We empirically study the application of controlled distortions of varying nature and strength, and their effect on human and machine recognizability. While human recognizability is measured on the basis of an extensive user study, machine recognizability is based on three memory-based content-based image retrieval (CBIR) and matching algorithms. We give a detailed description of our experimental image CAPTCHA system, IMAGINATION, that uses systematic distortions at its core. A significant research topic within the multimedia community, CBIR is actually conceived here as a tool for an adversary, so as to help us design secure image CAPTCHAs by understanding their limitations.