Characterizing Suspicious Images in Social Media Using EXIF Metadata
Online social networks (OSNs) have experienced tremendous growth in recent years and become a de facto portal
for hundreds of millions of Internet users.Media sharing applications on internet contain a huge amount of pictures that need
to be organized to facilitate browsing and retrieval. Images sent via online lately are becoming one of the main sources of
attack to the client machine. Images are vulnerable to malicious embedded hidden data, most often because of the image
contents are made attractive and code is hidden behind with executable. When those images are opened in some image
viewer, they are vulnerable to execute the piece of code embedded in images, leaves behind the virus/worm on the machine.
In the proposed system of image metadata extraction, there is provision of discarding the malicious images. This
characterization is based upon the detailed skin tone analysis performed to affirm the presence of vulgar content in the
images. We will try to show result experimentally that the proposed system performs well and fast in detecting vulgar
images. The images should be reviewed whether they are malicious before they are opened so that the client can be
prevented from being infected from malware.