philip lelyveld The world of entertainment technology

Facebook develops new method to reverse-engineer deepfakes and track their source

Deepfakes aren’t a big problem on Facebook right now, but the company continues to fund research into the technology to guard against future threats. Its latest work is a collaboration with academics from Michigan State University (MSU), with the combined team creating a method to reverse-engineer deepfakes: analyzing AI-generated imagery to reveal identifying characteristics of the machine learning model that created it.

Previous studies in this area have been able to determine which known AI model generated a deepfake, but this work, led by MSU’s Vishal Asnani, goes a step further by identifying the architectural traits of unknown models. These traits, known as hyperparameters, have to be tuned in each machine learning model like parts in an engine. Collectively, they leave a unique fingerprint on the finished image that can then be used to identify its source.

Identifying the traits of unknown models is important, Facebook research lead Tal Hassner tells The Verge, because deepfake software is extremely easy to customize. This potentially allows bad actors to cover their tracks if investigators were trying to trace their activity.

Not only can the resulting algorithm fingerprint the traits of a generative model, but it can also identify which known model created an image and whether an image is a deepfake in the first place. “On standard benchmarks, we get state-of-the-art results,” says Hassner.

But it’s important to note that even these state-of-the-art results are far from reliable. When Facebook held a deepfake detection competition last year, the winning algorithm was only able to detect AI-manipulated videos 65.18 percent of the time. Researchers involved said that spotting deepfakes using algorithms is still very much an “unsolved problem.”

See the full story here: https://www.theverge.com/2021/6/16/22534690/facebook-deepfake-detection-reverse-engineer-ai-model-hyperparameters