Social tags have become an important tool for improving access to online resources, particularly non-text media. With the dramatic growth of user-generated content, the importance of tags is likely to grow. However, while tagging behavior is well studied, the relationship between tagging behavior and features of the media being tagged is not well understood. In this paper, we examine the relati...

With the growing and prevalent usage of Internet, threat for the service providers has arisen. One of the most important aspects of modern security concerns is to deal with users that are computer programs or bots. These programs pretend to be human users and exploit servers by submitting data automatically, thereby, hindering the services of the server. Security mechanism dealing with such att...

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 prob...

Visual cryptography (VC) technique encodes an image into two or more shares that appear random in human eyes. In the decryption section, pixels shared images are combined to obtain information contained original image. This study applies visual cryptographic techniques graysle and color for user authentication online transactions using VC2,2 scheme. The server computer CAPTCHA sent through diff...

In this paper we present a model for multifaceted tagging, i.e. tagging enriched with contextual information. We present TagMe!, a social tagging front-end for Flickr images, that provides multifaceted tagging functionality: It enables users to attach tag assignments to a specific area within an image and to categorize tag assignments. Moreover, TagMe! maps tags and categories to DBpedia URIs t...

We describe a setup and experiments where users are checking and correcting image tags given by an automatic tagging system. We study how much the application of a content-based image retrieval (CBIR) method speeds up the process of finding and correcting the erroneously-tagged images. We also analyze the use of implicit relevance feedback from the user’s gaze tracking patterns as a method for ...

Crowdsourcing has been emerging to harvest social wisdom from thousands of volunteers to perform series of tasks online. However, little research has been devoted to exploring the impact of various factors such as the content of a resource or crowdsourcing interface design to user tagging behavior. While images’ titles and descriptions are frequently available i...

reCaptcha is a very popular CAPTCHA system on the Internet. Due to its design, we find that reCaptcha figures have certain feature that can potentially weaken this system. This paper discussed the design of reCaptcha, and use some simple Machine Learning algorithm to find a way to tell the difference between “control word” and “unknown word”. We also designed the experiment to evaluate our hypo...

CAPTCHAs have been deployed ubiquitously by web sites to combat automated malicious programs. Security against web bots and usability to legitimate users are two main goals that have to be simultaneously satisfied when designing a useful CAPTCHA scheme. However, there exists a well-known and intricate trade-off between these goals. So far, balancing this trade-off remains an art rather than a s...