Google has released a dataset of ~3,000 deepfake videos to help researchers develop deepfake detection techniques
Deep learning has given rise to technologies that would have been thought impossible only a handful of years ago. Modern generative models are one example of these …
Google AI Blog
Related Coverage
- Google has released a giant database of deepfakes to help fight deepfakes MIT Technology Review · Charlotte Jee
- Google fights deepfakes by releasing 3,000 deepfakes Engadget · Mariella Moon
- Google aiming to improve Deepfake detection by releasing example videos 9to5Google · Damien Wilde
- Google releases trove of deepfake videos so researchers can help fight them Fast Company · Michael Grothaus
- Google releases trove of deepfake videos to help researchers devise detection methods The Next Web · Ivan Mehta
- Google releases data set to help defeat deepfake videos VentureBeat · Kyle Wiggers
Discussion
-
@googleai
@googleai
on x
In collaboration with @Jigsaw and in partnership w/ the FaceForensics video benchmark team, we are excited to release a large dataset of visual deepfakes to directly support deepfake detection efforts. Learn more and find the data at https://ai.googleblog.com/... https://twitter.…
-
@sundarpichai
Sundar Pichai
on x
Detecting deepfakes is one of the most important challenges ahead of us. Following our release of a synthetic audio dataset in Jan, we're releasing a large dataset of visual deepfakes to support researchers working on synthetic video detection #GoogleAI https://ai.googleblog.com/…
-
@yasmind
Yasmin Green
on x
The largest and most diverse public dataset of #deepfakes is now available for research into detection algorithms — kudos @gullyand, @ndufour and @chrisbregler of @Jigsaw and @GoogleAI ! https://twitter.com/...
-
@jason_kint
Jason Kint
on x
Thank you for releasing this, Sundar. https://twitter.com/...
-
@samgregory
@samgregory
on x
+1 #deepfakes dataset to enhance detection - this time via @GoogleAI. We need coordination + sharing of datasets (esp once #deepfakes are + widespread) and real attention on how ensure detection methods= accessible, explainable, relevant to real-world + who is harmed by deepfakes…
-
@techreview
@techreview
on x
It includes 3,000 AI-generated videos that were made using various publicly-available algorithms.The context: Over the past year, generative algorithms have got so good at synthesizing media that what they produce could soon become indistinguishable ... https://www.technologyrevi…
-
@r_d
R. David Edelman
on x
Both @facebook & @Google are taking notable steps to advance deepfake research, detection. Worth asking what other areas of technical trust/safety need similar acceleration. https://twitter.com/...