Conspirador Norteño Profile picture
Nov 1, 2020 18 tweets 8 min read Read on X
We've done a decent amount of research on the use of GAN-generated images over the last two years, mostly fake face "photos" such as those produced by thispersondoesnotexist(dot)com. Here are all of our related threads in one place.

cc: @ZellaQuixote
GAN is an abbreviation for "generative adversarial network", the AI technique used to produce these images (and other things). Here's a "brief" description of how StyleGAN, the GAN behind thispersondoesnotexist(dot)com, works.
machinelearningmastery.com/introduction-t…
Here's the first network we found in the wild using GAN-generated face pics (29 of 52 accounts, created in two batches). The profiles featured repetitive biographies mentioning family, friends, country, and weapons.

Next up, a coronavirus/bitcoin-themed botnet from March 2020. 16 of 28 accounts used GAN-generated face pics.
In May 2020, we ran into a set of five fake pro-Biden accounts, all using the same GAN-generated profile pic. These accounts self-deleted shortly after this thread was posted.
Our first stab at a programmatic method for detecting GAN-generated face pics. This technique is designed to make the GAN-generated pictures easier to notice in groups of thousands of images - it isn't terribly accurate for individual images.
From May 2020, a 41 account Spanish-language botnet using GAN-generated profile images, with a focus on Argentina.
Next, a 4chan op using accounts with GAN-generated pics to push the #BernReturn hashtag alongside a bogus claim that Bernie Sanders was returning campaign donations.
Speaking of 4chan, thispersondoesnotexist(dot)com is quite popular over there, and folks frequently suggest using it as a source of profile pics for bogus Twitter accounts.


Here's a thread on now-suspended part-automated political troll account @Juan6million. This account mostly pushed left-wing messaging and hashtags, but also promoted alt-right talking points and influencers such as @MrAndyNgo.
The most prolific use of GAN-generated profile pics we've seen thus far was from the "Thousand Followers" follower-buying website (presently on hiatus). 8727 of 17957 of the fake Twitter followers provided by this site used GAN-generated images.
From August 2020, a mixed commerical/political retweet botnet consisting of 21 accounts using GAN-generated face pics.
We've run across a couple of botnets promoting cryptocurrency sites that use GAN-generated profile pics: 41 accounts pushing cointelegraph(dot)com and 28 accounts pushing ethereumcryptocurrency(dot)com.

Deepfake human faces are not the only sort of images one can produce with GANs. Here's a thread on GAN-generated anime pics, and the detection thereof:
From November 2020, a fake follower/retweet botnet using GAN-generated profile pics (164 accounts).
A similar network follower/retweet botnet created in August 2020. 53 accounts, all using GAN-generated pics. It mostly amplifies Russian-language accounts.
Thread on a weird automated account (@Jtatejtate1) using a GAN-generated face. A bunch of its followers are part of a recently reactivated botnet from 2013.
Using reverse image search to find Twitter accounts using GAN-generated profile pics:

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with Conspirador Norteño

Conspirador Norteño Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @conspirator0

Jul 20
Here's a look at how Community Notes handled misinformation regarding the Trump rally shooting. Short version: it's a mixed bag.

cc: @ZellaQuixote
conspirator0.substack.com/p/community-no…
screenshot of Substack post header
THE GOOD:

• Community Notes successfully placed fact checks on some of the most viral false posts about the shooting
• ~42% of noted posts were subsequently deleted by their authors
• An effort to spread a misidentification of the shooter via Community Notes failed screenshot of three attempts by user Notable Grass Eagle to insert false Community Notes regarding the shooter's identity
THE BAD:

• Community Notes fact checks take several hours to show up, which doesn't help much in the initial "breaking news" phase after a violent event
• Many notes never accumulate enough ratings to determine their fate
chart showing the post time and time of appearance of Community Notes for posts about the Trump assassination attempt with Community Notes
hourly volume chart for Community Notes regarding the Trump assassination attempt
Read 4 tweets
May 29
12 questions for @TheDailyBeast regarding @JakeLahut's false April 2023 story, "How Ron DeSantis Is Taking a Page Out of Nixon’s Playbook", which (among other things) falsely portrays an AI-generated face as a "sexually graphic meme" of a real child.

@JoannaColes @TracyConnor
four paragraphs from The Daily Beast containing a bizarre false anecdote about a "sexual meme" of a child (actually a GAN-generated face)
a GAN-generated face from thispersondoesnotexist.com that resembles a male child
First, some background and a couple debunks of the false article, for those unfamiliar with the situation:


conspirator0.substack.com/p/the-bot-farm…
medium.com/@EJGibney/how-…
1. How did the decision to use serial fabulist Steven Jarvis as a source for this article come about?

2. Was anyone employed by or affiliated with The Daily Beast at the time the article was published aware of Steven Jarvis's extensive history of making false claims?
Read 12 tweets
Jan 25
Meet @LovewinnLove (permanent ID 2707213009), a blue-check verified account with a GAN-generated face and a few additional odd characteristics. Despite being created in 2014, this account has no posts prior to October 2023.

cc: @ZellaQuixote screenshot of @LovewinnLove's profile, showing the account was created in 2014, and search results showing no posts from the account prior to October 10th, 2023
There are multiple indicators that @LovewinnLove's "face" is GAN-generated:

• unrealistic teeth (visible portion of bottom teeth is especially bizarre)
• odd texturing and seams in shirt fabric
• telltale eye positioning (more info in next post) @LovewinnLove's profile image, a GAN-generated face
@LovewinnLove All unmodified StyleGAN-generated face images have the property that the major facial features (particularly the eyes) are in the same position on each image. Blending @LovewinnLove's profile image with 99 other GAN-generated faces demonstrates this nicely.
Read 14 tweets
Dec 31, 2023
It's New Year's Eve, and a bunch of politics enthusiasts with GAN-generated faces are enthusiastically replying to a variety of posts with similarly-worded replies. #NewYearShenaniGANs

cc: @ZellaQuixote collage of 10 replies containing variations on "politics enthusiast" from accounts that use GAN-generated faces as avatars
The politics enthusiasts are part of a spam network consisting of (at least) 575 accounts created between May and December 2023 with GAN-generated faces. Many of their handles, such as @Maairiuieinaaa and @eJooeiaAoneueer, contain long strings of vowels.
histogram of account creation dates
table of example accounts from the network
@Maairiuieinaaa @eJooeiaAoneueer All 575 of these accounts use StyleGAN-generated faces as profile images. Some of these, such as @MauMoiagaia's profile image, contain a tiny "StyleGAN 2 (Karras et al.)" watermark in the lower right corner. collage of the GAN-generated faces that the accounts in the network use as profile images
Read 11 tweets
Dec 7, 2023
It's a great day to look at a network of inauthentic accounts that post identical AI art images (with a side of good old fashioned T-shirt spam).

cc: @ZellaQuixote


3 posts containing the same AI-generated image
3 posts containing the same AI-generated image
3 posts containing the same AI-generated image
3 posts containing the same AI-generated image
This network consists of 24 X accounts. 12 of these accounts were created in the latter half of 2023 and have female avatars, while the other 12 were created in 2013 or earlier and have male avatars.

table of the 24 accounts in the network
screenshots of the profiles of the 12 female-presenting accounts in the network, all created in 2023
screenshots of the profiles of the 12 male-presenting accounts in the network, all created in 2013 or earlier
The 12 accounts with female avatars and 2023 creation dates regularly post AI-generated art images, and these image posts are quickly reposted by other accounts in the network (both female and male). The AI-generated images are often duplicated across accounts.


examples of AI art images posted by the network, and screenshots of the reposts
3 posts containing the same AI-generated image
3 posts containing the same AI-generated image
3 posts containing the same AI-generated image
Read 8 tweets
Sep 1, 2023
Meet @ImJamesMiller (permanent ID 1371651462153994242), an account with a GAN-generated face, 172K followers, and no tweets prior to two days ago. What's up with that?

cc: @ZellaQuixote screenshot of @ImJamesMiller's profile, screenshot of tweeterid.com lookup showing @ImJamesMiller's permanent ID, and closeup of @ImJamesMiller's profile image, a GAN-generated face
As it turns out, @ImJamesMiller wasn't always named @ImJamesMiller. In June, the account was named @/IamJimCaviezel in an apparent attempt to impersonate Sound of Freedom actor Jim Caviezel.

web.archive.org/web/2023062319…
screenshot of wayback machine archive
@ImJamesMiller Multiple prominent users appear to have accepted the fake Jim Caviezel account as legitimate, including Texas Congressman Brian Babin, right-wing influencer/ex-Game of Thrones blogger Jack Posobiec, and recently indicted ex-Assistant Attorney General Jeff Clark. screenshots of tweets from large accounts tagging the fake Jim Caviezel account
Read 9 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

:(