Digital Image Forensics Lecture 1

Image Forgery Definition

• Image forgery means manipulating a digital original image to conceal meaningful information.
• The detection of forged images is driven by the need for authenticity and to maintain the integrity of the image.
• Editing a real-world photo through computer software or mobile applications is not considered forgery, even though it has been altered from its original capture.
• Forgery can be committed for gain and prestige, creating an image to dupe the recipient into believing it is real.

Image Forgery Example

• Swapping two faces using auto face swap software is an example of image forgery.

History of Photo Manipulation

• 1860: The portrait of Abraham Lincoln is a composite of Lincoln's head and John Calhoun's body.
• 1864: A composite image of General Ulysses S. Grant in front of his troops at City Point, with the head from one picture and the horse and body from another.
• 1930: Photo manipulation has been used for various purposes.
• 1942: Benito Mussolini had the horse handler removed from the original photograph to create a more heroic portrait of himself.
• 1997: A forged image was created, with the original and forged images shown side by side.
• 2004: Another example of photo manipulation, with the original and forged images shown side by side.
• 2008: A forged image was created, with the original and forged images shown side by side.

Type of Forgery

• There are three types of forgery:
  • An image created using graphical software.
  • An image where the content has been altered.
  • An image where the context has been altered.

Using Graphical Software

• Images can be created using graphical software, making it difficult to determine what is real and what is computer-generated.

Image Forgery Types

• The content has been altered: A forged image can be created by altering the content of its original image, duping the recipient into believing that the objects in an image are something else.
• The context has been altered: Objects can be removed or added, for example, a person can be added or removed from an image.

Digital Image Forensics

• Active techniques are based on inserting watermarks or signatures in digital images during recording.
• The authenticity is determined by checking if the extracted watermark from the image matches the original watermark.

Digital Watermark Drawbacks

• Digital cameras must be equipped with a watermark insertion mechanism during recording, which would limit this technique to be used with special cameras.
• Watermarks can be weak and may be destroyed when a watermarked image is compressed using a compressing algorithm like JPEG.
• It is not possible to decide if a watermark has been inserted after image manipulation or not.

Process of Digital Forensics

• Identification: The first step in the process, including where the evidence is found, preserved, and stored.
• Preservation: The evidence is stored in an isolated place to secure and preserve it from any tampering.
• Analysis: Reviewing the identified evidence to determine the accuracy of the results, looking for any additional data that might help answer questions about the case.
• Documentation: Drawing a series of all possible evidence of data from the given inputs.