Abstract:In this paper, we propose an innovative type of CAPTCHA (Completely Automated Public Turing test to tell Computers and Humans Apart). These tests are used to allow a service to discriminate human user...In this paper, we propose an innovative type of CAPTCHA (Completely Automated Public Turing test to tell Computers and Humans Apart). These tests are used to allow a service to discriminate human users from (malicious) bots. With FATCHA, the user is simply asked to perform at random some trivial gesture, e.g., moving the head, which will be captured by the computer webcam and recognized by the server hosting the service. A second module in a possible composite service allows the user to authenticate by face recognition instead of using a password. In this way we significantly exploit the potentiality of multimodal interaction for both an advanced Human Interactive Proof (HIP) test and for robust/comfortable authentication.Read More