Synthetic Media & Generative AI News and Discussions

[weatheriscool]

[caltrek]

UC Riverside Scientists Develop Tool to Detect Fake Videos
July 24, 2025

Introduction:

(Eurekalert) In an era where manipulated videos can spread disinformation, bully people, and incite harm, UC Riverside researchers have created a powerful new system to expose these fakes.

Amit Roy-Chowdhury, a professor of electrical and computer engineering, and doctoral candidate Rohit Kundu, both from UCR’s Marlan and Rosemary Bourns College of Engineering, teamed up with Google scientists to develop an artificial intelligence model that detects video tampering — even when manipulations go far beyond face swaps and altered speech. (Roy-Chowdhury is also the co-director of the UC Riverside Artificial Intelligence Research and Education (RAISE) Institute, a new interdisciplinary research center at UCR.)

Their new system, called the Universal Network for Identifying Tampered and synthEtic videos (UNITE), detects forgeries by examining not just faces but full video frames, including backgrounds and motion patterns. This analysis makes it one of the first tools capable of identifying synthetic or doctored videos that do not rely on facial content.

“Deepfakes have evolved,” Kundu said. “They’re not just about face swaps anymore. People are now creating entirely fake videos — from faces to backgrounds — using powerful generative models. Our system is built to catch all of that.”

Conclusion:

“People deserve to know whether what they’re seeing is real,” Kundu said. “And as AI gets better at faking reality, we have to get better at revealing the truth.”

Read more of the Eurekalert article here: https://www.eurekalert.org/news-releases/1092437

The researchers presented their findings in a paper that can be read here: https://arxiv.org/pdf/2412.12278

[raklian]

[firestar464]

Releasing Open Weights for FLUX.1 Krea

https://www.krea.ai/blog/flux-krea-open-source-release

[caltrek]

Hiding Secret Codes in Light Protects Against Fake Videos
July 31, 2025

Introduction:

(Eureklaert) ITHACA, N.Y. – Fact-checkers may have a new tool in the fight against misinformation. A team of Cornell University researchers has developed a way to “watermark” light in videos, which they can use to detect if video footage is fake or has been manipulated.

The idea is to hide information in nearly-invisible fluctuations of lighting at important events and locations, such as interviews and press conferences or even entire buildings, like the United Nations Headquarters. These fluctuations are designed to go unnoticed by humans, but are recorded as a hidden watermark in any video captured under the special lighting, which could be programmed into computer screens, photography lamps and built-in lighting. Each watermarked light source has a secret code that can be used to check for the corresponding watermark in the video and reveal any malicious editing.

Peter Michael, a graduate student in the field of computer science who led the work, will present the study on August 10 at SIGGRAPH 2025 in Vancouver, British Columbia.

“Video used to be treated as a source of truth, but that’s no longer an assumption we can make,” said Abe Davis, assistant professor of computer science, who first conceived of the idea. “Now you can pretty much create video of whatever you want. That can be fun, but also problematic, because it’s only getting harder to tell what’s real.”

To address these concerns, researchers had previously designed techniques to watermark digital video files directly, with tiny changes to specific pixels that can be used to identify unmanipulated footage or tell if a video was created by AI. However, these approaches depend on the video creator using a specific camera or AI model – a level of compliance that may be unrealistic to expect from potential bad actors.

Read more here: https://www.eurekalert.org/news-releases/1093248

caltrek: A lot will depend on the game of who do you trust. I can imagine the following dialogue:

Expert: Through the use of watermarks, we have determined that this video is a fake, that it is derived from an original vide that has been dramatically altered.

MAGA person: You are just saying that because you are a liberal.

Worse yet could be deepfakes that are widely circulated without warnings that they are fake despite expert detection.

[wjfox]

This seems ghoulish...

[zzz]

This seems ghoulish...

It is no different from animating a photo on crazytalk.

[firestar464]

This seems ghoulish...

Replies are filled with scumbags missing the fucking point. The damn point is to age him up to make a point.

[weatheriscool]

[weatheriscool]

[weatheriscool]

[weatheriscool]

[firestar464]

Genie but blurry?

[wjfox]

[firestar464]

once again, this is why people should not believe everything they see on the internet

[firestar464]

[wjfox]

The influencer in this Vodafone ad isn’t real

Sep 8, 2025, 11:18 AM GMT+1

I opened TikTok while visiting Germany last week and stumbled across a Vodafone ad being presented by a woman who probably doesn’t exist. The ad includes several “tells” that suggest the presenter was artificially created using generative AI — the unnatural style and movement of her hair, the way her moles disappear, and the uncanny valley vibe of her facial expressions — and Vodafone confirmed my suspicions in its video comments.

In response to a commenter asking why Vodafone couldn’t put “a real person in front of the camera,” the company said it was “testing different styles of advertising — this time with AI,” according to machine translation of the German text. In another comment, Vodafone said that “AI is so much a part of everyday life these days that we also try it out in advertising.”

https://www.theverge.com/news/773567/vo ... ter-tiktok

[firestar464]

when will companies realize that synthetic media is not popular in the developed world?

[spryfusion]

[wjfox]