Researchers Come Out With Yet Another Unnerving, New Deepfake Method

["Dave Farber" <farber () gmail com>]

Begin forwarded message:

> From: Dewayne Hendricks <dewayne () warpspeed com>
> Date: September 12, 2018 at 4:46:57 PM GMT+9
> To: Multiple recipients of Dewayne-Net <dewayne-net () warpspeed com>
> Subject: [Dewayne-Net] Researchers Come Out With Yet Another Unnerving, New Deepfake Method
> Reply-To: dewayne-net () warpspeed com
>
> [Note:  This item comes from friend Judi Clark.  DLH]
>
> Researchers Come Out With Yet Another Unnerving, New Deepfake Method
> By Melanie Ehrenkranz
> Sep 11 2018
> <https://gizmodo.com/researchers-come-out-with-yet-another-unnerving-new-de-1828977488>
>
> Deepfakes, ultrarealistic fake videos manipulated using machine learning, are getting pretty convincing. And 
> researchers continue to develop new methods to create these types of videos, for better or, more likely, for worse. 
> The most recent method comes from researchers at Carnegie Mellon University, who have figured out a way to 
> automatically transfer the “style” of one person to another.
>
> “For instance, Barack Obama’s style can be transformed into Donald Trump,” the researchers wrote in the description 
> of a YouTube video highlighting the outcome of this method. The video shows the facial expressions of John Oliver 
> transferred to both Stephen Colbert and an animated frog, from Martin Luther King, Jr. to Obama, and from Obama to 
> Trump.
>
> The first example seen—Oliver to Colbert—is far from the most realistic manipulated video out there. It looks 
> low-res, with certain facial features blurring at certain points. It’s almost as if you’re trying to stream an 
> interview from the internet but you have incredibly weak wifi. The other examples (excluding the frog) are certainly 
> more convincing, showing the deepfake mirroring the facial expression and mouth movements of the original subject.
>
> The researchers describe the process in a paper as an “unsupervised data-driven approach.” Like other methods of 
> developing deepfakes, this one uses artificial intelligence. The paper doesn’t exclusively deal in translating 
> talking style and facial movements from one human to another—it also includes examples with blooming flowers, 
> sunrises and sunsets, and clouds and wind. For the person-to-person deepfakes, the researchers cite examples of how 
> certain mannerisms can be transferred, including “John Oliver’s dimple while smiling, the shape of mouth 
> characteristic of Donald Trump, and the facial mouth lines and smile of Stephen Colbert.” The team used videos 
> available to the public to develop these deepfakes.
>
> It’s easy to see how these techniques might be applied in a more innocuous way. The example of John Oliver and the 
> cartoon frog, for instance, points to a potentially useful tool when it comes to developing realistic, 
> anthropomorphic animations. But as we’ve seen, there are consequences to the proliferation of increasingly realistic 
> deepfakes—and equipping bad actors with tools that make them cheap and easy to create. In time, they may dangerously 
> mislead the public, and can serve as a nefarious tool for political propaganda.



-------------------------------------------
Archives: https://www.listbox.com/member/archive/247/=now
Modify Your Subscription: https://www.listbox.com/member/?member_id=18849915
Unsubscribe Now: 
https://www.listbox.com/unsubscribe/?member_id=18849915&id_secret=18849915-a538de84&post_id=20180912045006:D6969EF4-B668-11E8-81C8-DCE310600BFA
Powered by Listbox: https://www.listbox.com