Flasher Detection Project in Online and Mobile Video Chat A key area of CyberSafety research that we are exploring concerns making the Internet safer for users of popular random video chat applications like Chatroulette and Omegle. In such applications, one of the major problems experienced by users is that of flasher misbehavior. Such misbehavior can be distasteful and potentially illegal if minors are present on the site. Our research consists of the following efforts:
Flasher Detection Analysis on Random Web Video Chat Application Our previous studies about detecting flasher on random web video chat are shown in safevchat.org Flasher Detection Analysis on Random Mobile Video Chat Application Online video chat services such as Chatroulette and Omegle randomly match users in video chat sessions and have become increasingly popular, with tens of thousands of users online at anytime during a day. Our interest is in examining user behavior in the growing domain of mobile video, and in particular how users behave in such video chat services as they are extended onto mobile clients. To date, over four thousand people have downloaded and used our Android-based mobile client, which was developed to be compatible with an existing video chat service. Our project provides a first-ever detailed large scale study of mobile user behavior in a random video chat service over a three week period. This study identifies major characteristics such as mobile user session durations, time of use, demographic distribution and the large number of brief sessions that users click through to find good matches. Through content analysis of video and audio, as well as analysis of texting and clicking behavior, we discover key correlations among these characteristics, e.g., normal mobile users are highly correlated with using the front camera and with the presence of a face, whereas misbehaving mobile users (flasher) have a high negative correlation with the presence of a face. A screenshot of the MVChat application. We label the snapshots in long sessions and those sessions (by major voting from image labels) into multiple taxonomies. And then we analyze the correlations between different taxonomies and try to identify behavioral characteristics which are likely or unlikely to occur together. Below summarizes the key results of our taxonomy correlation analysis, including strong positive (negative) correlations, some (surprising) non-correlations, and one-directional association rules with high confidence values on both image(L) and session(R) level. Our interesting and important findings include: Normal users are highly correlated with using the front camera and showing their faces, whereas misbehaving users tend to hide their faces – which suggests the exploration of camera position and face detection for distinguishing normal users from misbehaving ones; Users with a large enough fraction of sustained sessions are disproportionately female, but surprisingly females were just as likely to misbehave as males. Figure (d) Taxonomy correlation analysis: (L) image-based graph and (R) session-based graph. Highlighted in the graphs are strong positive correlations (both all_conf and cosine are > 0.85), strong negative correlations (both all_conf and cosine are < 0.1), some non-correlations (X^2 is close to 0 and lift is close to 1), and association rules with confidence > 0.8. To learn more interesting findings in our project, you can go to here for details. |