Deepfakes have been jolting the media for quite some time now and creating unnecessary stirs in the international world. For instance, the picture shown here displays Barrack Obama’s tailored video shows signs of facial mapping. With deepfakes, you can put words in the mouth of people that they have never uttered.
Fortunately, these deepfakes can be caught now. Using AI, the perpetrators can also be caught; reverse engineering is the key here.
Deepfakes are altered photos, videos, and still images that use artificial intelligence to appear like the real thing. They’ve become increasingly realistic in recent years, making it harder to detect the real from the fake with just the naked eye.
Deepfakes are tailored photos, videos, and stills that can be presented as real with the help of AI. Unfortunately, they have become a menace and more lifelike in the near past, making it extremely difficult for laymen to understand the difference.
Deepfakes have the capacity to upend global celebrities and world leaders if malicious deepfakes are released in their guise.
Deepfakes of Tom Cruise, Former President Barack Obama, and House Speaker Nancy Pelosi went viral and have made onlookers realize the potency of the damages that can be done using the highly advanced deepfakes.
“Our method will facilitate deepfake detection and tracing in real-world settings, where the deepfake image itself is often the only information detectors have to work with,” research scientists for Facebook Xi Yin and Tal Hassner told.
The work was done as a joint effort with Michigan State University.
“In digital photography, fingerprints are used to identify the digital camera used to produce an image,” the researchers explained. Those fingerprints are one of a kind patterns “that can equally be used to identify the generative model that the image came from.”
The researchers say that his program has the potential to change the scenarios in which people are targeted, and people with mal intent get away with their wrongdoings. This research will provide “tools to better investigate incidents of coordinated disinformation using deepfakes, as well as open up new directions for future research.”