
First and second columns show the original im- ages and manipulated ones respectively. The black and white images in the third column are corresponding bi- nary GT masks. Predicted masks (column 4) and generated CAMs (column 5) for manipulated images from Face2Face (row 1,2,3) and Neural-Textures (row 4,5,6) dataset.
(Mazaheri & Roy-Chowdhury, 2022)
Two-pronged technique detects manipulated facial expressions and identity swaps
Computer scientists at UC Riverside can detect manipulated facial expressions in deepfake videos with higher accuracy than current state-of-the-art methods. The method also works as well as current methods in cases where the facial identity, but not the expression, has been swapped, leading to a generalized approach to detect any kind of facial manipulation. The achievement brings researchers a step closer to developing automated tools for detecting manipulated videos that contain propaganda or misinformation.
Developments in video editing software have made it easy to exchange the face of one person for another and alter the expressions on original faces. As unscrupulous leaders and individuals deploy manipulated videos to sway political or social opinions, the ability to identify these videos is considered by many essential to protecting free democracies. Methods exist that can detect with reasonable accuracy when faces have been swapped. But identifying faces where only the expressions have been changed is more difficult and to date, no reliable technique exists.
“What makes the deepfake research area more challenging is the competition between the creation and detection and prevention of deepfakes which will become increasingly fierce in the future. With more advances in generative models, deepfakes will be easier to synthesize and harder to distinguish from real,” said paper co-author Amit Roy-Chowdhury, a Bourns College of Engineering professor of electrical and computer engineering.
The UC Riverside method divides the task into two components within a deep neural network. The first branch discerns facial expressions and feeds information about the regions that contain the expression, such as the mouth, eyes, or forehead, into a second branch, known as an encoder-decoder. The encoder-decoder architecture is responsible for manipulation detection and localization.
The framework, called Expression Manipulation Detection, or EMD, can both detect and localize the specific regions within an image that have been altered.
“Multi-task learning can leverage prominent features learned by facial expression recognition systems to benefit the training of conventional manipulation detection systems. Such an approach achieves impressive performance in facial expression manipulation detection,” said doctoral student Ghazal Mazaheri, who led the research.
The benchmark datasets for facial manipulation are based on expression and identity swap. One transfers the expressions of a source video onto a target video without changing the identity of the person in the target video. The other swaps two identities in a single video.
Experiments on two challenging facial manipulation datasets show EMD has better performance in detection of not only facial expression manipulations but also identity swaps. EMD accurately detected 99% of the manipulated videos.
Original Article: New method detects deepfake videos with up to 99% accuracy
More from: University of California Riverside
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
Deepfake videos
- From a Deepfaked Elon Musk to RadioShack’s NSFW Tweets, CMO Today’s Twenty-Two Most-Read Stories of 2022
Famous brands tried winning consumers with more AI and less reliance on search advertising, as well as rafts of obscene tweets.
- Why three robot sisters could be the friendly face of AI
Artificial intelligence has become an integral part of our everyday lives, but not everyone is comfortable with the idea. The key to winning over a skeptical public could be a family of robot "sisters ...
- Kendrick Lamar’s New Chapter: Raw, Intimate and Unconstrained
In partnership with his longtime collaborator, Dave Free, the greatest rapper of his generation is pushing himself — commercially and creatively — onto unexpected terrain.
- Deepfakes: Get ready for phishing 2.0
While the most common form of phishing is still via email, we’re seeing an uptick in phishing that combines the use of voice , social media, and SMS (aka smishing) to appear mor ...
- ‘South Park’ Creators Trey Parker and Matt Stone Land $20 Million in Funding for Their Deepfake VFX Studio
Trey Parker and Matt Stone are going deeper into Deep Voodoo. The creators of “South Park” have secured a $20 million investment for their AI entertainment startup Deep Voodoo. The ...
Go deeper with Google Headlines on:
Deepfake videos
[google_news title=”” keyword=”deepfake videos” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]
Go deeper with Bing News on:
Expression Manipulation Detection
- Crypto Manipulation Has Consequences
Matt Levine is a Bloomberg Opinion columnist covering finance. He was an editor of Dealbreaker, an investment banker at Goldman Sachs, a mergers and acquisitions lawyer at Wachtell, Lipton, Rosen ...
- No match manipulation detected at FIFA World Cup™
The multi-stakeholder Integrity Task Force established by FIFA to monitor all matches played during the FIFA World Cup 2022™ for match-manipulation incidents and integrity-related issues ...
- Coherent manipulation of spin qubits at room temperature
More information: Xuyang Lin et al, Room-temperature coherent optical manipulation of hole spins in solution-grown perovskite quantum dots, Nature Nanotechnology (2022). DOI: 10.1038/s41565-022 ...
- Chiropractic spinal manipulation associated with reduction in low back surgery
A recent study from University Hospitals (UH) Connor Whole Health has found that adults who initially visit a chiropractor to receive spinal manipulation for low back pain caused by disc ...
- Three Tessier-Lavigne papers issued Editorial Expressions of Concern
Science and Cell have published Editorial Expressions of Concern for three ... wrote in a Nov. 28 statement that the images with alleged manipulation in the three papers “do not affect the ...
Go deeper with Google Headlines on:
Expression Manipulation Detection
[google_news title=”” keyword=”Expression Manipulation Detection” num_posts=”5″ blurb_length=”0″ show_thumb=”left”]