Captcha-asiaCCS10 - Scene Tagging: Image-Based CAPTCHA...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
345 Scene Tagging: Image-Based CAPTCHA Using Image Composition and Object Relationships Peter Matthews School of Electrical Engineering & Computer Science University of Central Florida Orlando, FL 32816 [email protected] Cliff C. Zou School of Electrical Engineering & Computer Science University of Central Florida Orlando, FL 32816 [email protected] ABSTRACT In this paper, we propose a new form of image-based CAPTCHA we term “scene tagging”. It tests the ability to recognize a relationship between multiple objects in an image that is automatically generated via composition of a background image with multiple irregularly shaped object images, resulting in a large space of possible images and questions without requiring a large object database. This composition process is accompanied by a carefully designed sequence of systematic image distortions that makes it difficult for automated attacks to locate/identify objects present. Automated attacks must recognize all or most objects contained in the image in order to answer a question correctly, thus the proposed approach reduces attack success rates. An experimental study using several widely-used object recognition algorithms (PWD-based template matching, SIFT, SURF) shows that the system is resistant to these attacks with a 2% attack success rate, while a user study shows that the task required can be performed by average users with a 97% success rate. Categories and Subject Descriptors K.6.5 [ Management of Computing and Information Systems ]: Security and Protection General Terms Security Keywords CAPTCHA, HIP, access control; image/video recognition; multi- object composition; security 1. INTRODUCTION A number of abuses of Internet services are only made possible by the use of automated programs, such as the mass posting of spam to comment sections and user forums, mass user account registration, brute force password attacks, and abuse of online polls. To prevent such abuses, services may require a user to pass a CAPTCHA [1] (Computer Automated Turing Test for telling Computers and Humans Apart), a challenge-response test that can be easily solved by human users but is extremely difficult for computer programs and, hence, determines whether a service request originated from a human or an automated program. Such test systems are now in wide use on the Internet, and play a critical role in ensuring the integrity of many of the most popular websites. In order to be effective in this role, it is important that CAPTCHAs are strongly resistant to automated attacks and at the same time do not cause problems for human users. Text-based CAPTCHAs, in which users are required to transcribe text presented in a distorted image, make up the majority of CAPTCHA systems in real-world use. However, their vulnerability to attack has been repeatedly demonstrated by computer vision researchers [5, 15, 17]. For example, several commercial CAPTCHA implementations were attacked in 2004 by Microsoft researchers with 80%-95% success rates achieved
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 08/25/2011 for the course EEL 5937 taught by Professor Staff during the Spring '08 term at University of Central Florida.

Page1 / 6

Captcha-asiaCCS10 - Scene Tagging: Image-Based CAPTCHA...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online