Digital Image and Video Forensics
Spring 2008 - Present
Digital images are everywhere - from our cell phones to the pages of our online news sites. How we choose to use digital image processing raises a surprising host of legal and ethical questions that we must address. What are the ramifications of hiding data within an innocent image? Is this an intentional security practice when used legitimately, or intentional deception? Is tampering with an image appropriate in cases where the image might affect public behavior? Does an image represent a crime, or is it simply a representation of a scene that has never existed? Before action can even be taken on the basis of a questionable image, we must detect something about the image itself. Investigators from a diverse set of fields require the best possible tools to tackle the challenges presented by the malicious use of today's digital image processing techniques.
In this work, we are exploring the emerging field of digital image forensics, including the main topic areas of source camera identification, forgery detection, and steganalysis. In source camera identification, we seek to identify the particular model of a camera, or the exact camera, that produced an image. Forgery detection's goal is to establish the authenticity of an image, or to expose any potential tampering the image might have undergone. With steganalysis, the detection of hidden data within an image is performed, with a possible attempt to recover any detected data.
This work was supported by Air Force STTR Award No. FA9550-05-C-0172
- "Open Set Source Camera Attribution and Device Linking," (in press), , , , ,Pattern Recognition Letters (PRL),September 2013.
- "Open Set Source Camera Attribution," (Best Student Paper Award), , ,Proceedings of XXV SIBGRAPI - Conference on Graphics, Patterns and Images,August 2012.
- "Vision of the Unseen: Current Trends and Challenges in Digital Image and Video Forensics,", , , ,ACM Computing Surveys (CSUR),October 2011.
- "The Unseen Challenge Data Sets,", , , ,Proceedings of the First IEEE Workitorial on Vision of the Unseen,June 2008.
73,000 images incorporating stego content from eight different tools at varying channel capacities