Artificial intelligence to accurately detect altered photos is getting smarter
Seeing was believing until technology reared its mighty head and gave us powerful and inexpensive photo-editing tools. Now, realistic videos that map the facial expressions of one person onto those of another, known as deepfakes, present a formidable political weapon.
But whether it’s the benign smoothing of a wrinkle in a portrait, or a video manipulated to make it look like a politician saying something offensive, all photo editing leaves traces for the right tools to discover.
Research led by Amit Roy-Chowdhury’s Video Computing Group at the University of California, Riverside has developed a deep neural network architecture that can identify manipulated images at the pixel level with high precision. Roy-Chowdhury is a professor of electrical and computer engineering and the Bourns Family Faculty Fellow in the Marlan and Rosemary Bourns College of Engineering.
A deep neural network is what artificial intelligence researchers call computer systems that have been trained to do specific tasks, in this case, recognize altered images. These networks are organized in connected layers; “architecture” refers to the number of layers and structure of the connections between them.
Objects in images have boundaries and whenever an object is inserted or removed from an image, its boundary will have different qualities than the boundaries of objects in the image naturally. Someone with good Photoshop skills will do their best to make the inserted object looks as natural as possible by smoothing these boundaries.
While this might fool the naked eye, when examined pixel by pixel, the boundaries of the inserted object are different. For example, inserted boundaries are often smoother than the natural objects. By detecting boundaries of inserted and removed objects, a computer should be able to identify altered images.
The researchers labeled nonmanipulated images and the relevant pixels in boundary regions of manipulated images in a large dataset of photos. The aim was to teach the neural network general knowledge about the manipulated and natural regions of photos. They tested the neural network with a set of images it had never seen before, and it detected the altered ones most of the time. It even spotted the manipulated region.
“We trained the system to distinguish between manipulated and nonmanipulated images, and now if you give it a new image it is able to provide a probability that that image is manipulated or not, and to localize the region of the image where the manipulation occurred,” Roy-Chowdhury said.
The researchers are working on still images for now, but they point out that this can also help them detect deepfake videos.
“If you can understand the characteristics in a still image, in a video it’s basically just putting still images together one after another,” Roy-Chowdhury said. “The more fundamental challenge is probably figuring out whether a frame in a video is manipulated or not.”
Even a single manipulated frame would raise a red flag. But Roy-Chowdhury thinks we still have a long way to go before automated tools can detect deepfake videos in the wild.
“It’s a challenging problem,” Roy-Chowdhury said. “This is kind of a cat and mouse game. This whole area of cybersecurity is in some ways trying to find better defense mechanisms, but then the attacker also finds better mechanisms.”
He said completely automated deepfake detection might not be achievable in the near future.
“If you want to look at everything that’s on the internet, a human can’t do it on the one hand, and an automated system probably can’t do it reliably. So it has to be a mix of the two,” Roy-Chowdhury said.
Deep neural network architectures can produce lists of suspicious videos and images for people to review. Automated tools can reduce the amount of data that people — like Facebook content moderators — have to sift through to determine if an image has been manipulated.
For this use, the tools are right around the corner.
“That probably is something that these technologies will contribute to in a very short time frame, probably in a few years,” Roy-Chowdhury said.
The paper, “Hybrid LSTM and Encoder–Decoder Architecture for Detection of Image Forgeries,” is published in the July 2019 issue of IEEE Transactions on Image Processing and was funded by DARPA. Other authors include Jawadul H. Bappy, Cody Simons, Lakshmanan Nataraj, and B. S. Manjunath.
In related work, his group developed a method for detecting other types of image manipulation in addition to object insertion and removal. This method extends the identification of blurry boundaries into general knowledge about the kinds of transitions between manipulated and nonmanipulated regions to predict tampering more accurately than current tools.
Learn more: This deep neural network fights deepfakes
The Latest on: Deep fakes
[google_news title=”” keyword=”deep fakes” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Deep fakes
- AI deepfakes framed this Maryland school principal for being raciston April 26, 2024 at 5:41 am
According to court documents, Dazhon Darien faces charges that include stalking and retaliating against a witness.
- Senate pursues action against AI deepfakes in election campaignson April 26, 2024 at 3:00 am
A Senate hearing highlights the dangers of bogus, artificial intelligence materials in elections. A bill was introduced in 2023, but the urgency is now.
- Mass. House passes measure targeting ‘deepfakes’ in campaign adson April 25, 2024 at 6:44 pm
We gotta start having this conversation because we’re going to be chasing our tail if we don’t start thinking about it now," said the Massachusetts House's top Republican.
- AI deepfakes threaten to upend global elections. No one can stop them.on April 23, 2024 at 4:26 am
The only thing stopping us from creating unethical deepfakes is our ethics,” Jadoun told The Washington Post. “But it’s very difficult to stop this.” India’s elections, which began last week and run ...
- RI lawmakers move to ban political 'deepfakes' ahead of elections. What that means.on April 22, 2024 at 12:32 pm
Secretary of State Gregg Amore told legislators at a hearing late last month that so-called deepfakes have been used to deceive the public about statements and actions taken by political leaders in ...
- Deepfakes of Bollywood stars spark worries of AI meddling in India electionon April 21, 2024 at 8:34 pm
In fake videos that have gone viral online, two of India's A-lister Bollywood actors are seen criticizing Prime Minister Narendra Modi and asking people to vote for the opposition Congress party in ...
- India Offers a Glimpse Into the Rise of Campaign Deep Fakeson April 19, 2024 at 2:04 pm
On the Big Take podcast, a deep fake operation in India makes videos of candidates directly addressing voters — a trend that could soon spread globally.
- Big Take: Indian Election Contends with Deep Fakeson April 19, 2024 at 1:38 pm
Connecting decision makers to a dynamic network of information, people and ideas, Bloomberg quickly and accurately delivers business and financial information, news and insight around the world ...
- ‘Deepfakes’ are concerning but won’t stop the Olympic Games’ broadcaster from embracing AIon April 19, 2024 at 12:00 pm
As part of a push by the International Olympic Committee to embrace artificial intelligence (AI) in Paris, the Games’ broadcaster is stepping up its use of the technology—but not without concerns ...
- Games' broadcaster embracing AI but remains wary of deepfakeson April 19, 2024 at 7:42 am
As part of a push by the International Olympic Committee to embrace artificial intelligence (AI) in Paris, the Games' broadcaster is stepping up its use of the technology -- but not without concerns ...
via Bing News