Jump to content

Welcome to FutureTimeline.forum
Register now to gain access to all of our features. Once registered and logged in, you will be able to create topics, post replies to existing threads, give reputation to your fellow members, get your own private messenger, post status updates, manage your profile and so much more. If you already have an account, login here - otherwise create an account for free today!
Photo

Synthetic Media & Deepfakes News and Discussions

Artificial intelligence synthetic media deepfakes media synthesis GANs artificial imagination image synthesis natural language generation automation deep learning

  • Please log in to reply
183 replies to this topic

Poll: Synthetic Media Poll (5 member(s) have cast votes)

When will deepfakes be perfected?

  1. 2020 to 2022 (1 votes [20.00%])

    Percentage of vote: 20.00%

  2. 2022 to 2024 (3 votes [60.00%])

    Percentage of vote: 60.00%

  3. 2024 to 2026 (0 votes [0.00%])

    Percentage of vote: 0.00%

  4. After 2026 (1 votes [20.00%])

    Percentage of vote: 20.00%

Vote Guests cannot vote

#61
Yuli Ban

Yuli Ban

    Born Again Singularitarian

  • Moderators
  • PipPipPipPipPipPipPipPipPipPipPip
  • 21,025 posts
  • LocationNew Orleans, LA

Iraq Elections: Fake Sex Tapes Created to Taint Female Candidates

Deepfakes used to create humiliating and potentially dangerous videos

The release of sex tapes purportedly belonging to two female candidates in Iraq’s upcoming elections on the social media has sparked deep concerns among the country’s public opinion.
The main victims of the campaign, Hala Qasim al-Yaseri from the Civilized Alliance led by Faiq Al Sheikh Ali, and Entezar al-Shamri from the Victory Alliance led by Iraqi Prime Minister Haider al-Abadi, have vehemently denied the videos as fake.
They called the sex videos politically-motivated, according to a report by the Persian-language Islamic Republic News Agency (IRNA).
Experts say a new software application has been developed by Israel which can fabricate sex tapes drawing on the man or woman’s photos.
“The software is developed by the Zionist regime to tarnish the image of Muslims in the world and suppress the people who are against them,” experts say.
Following the release of the vulgar videos, Entezar al-Shamri who also serves as a university professor in Baghdad withdrew from the election competition. There is no report yet on the withdrawal of Hala Qasim al-Yaseri.

Surprised no one caught this story at the time. I could've sworn it would've been discussed more.


And remember my friend, future events such as these will affect you in the future.


#62
Yuli Ban

Yuli Ban

    Born Again Singularitarian

  • Moderators
  • PipPipPipPipPipPipPipPipPipPipPip
  • 21,025 posts
  • LocationNew Orleans, LA

Researchers trained an AI to create Flintstones cartoons - Training set contained 25,000+ Flintstones video clips, each of 75 frames(about 3s) in length. This could lead to entertainment being created from scratch by AI instead of studios full of people in future

 

Seriously, good god! How could anyone look at this and not go, "Yep, the entertainment industry is in mortal danger within the next 15 years."


And remember my friend, future events such as these will affect you in the future.


#63
Yuli Ban

Yuli Ban

    Born Again Singularitarian

  • Moderators
  • PipPipPipPipPipPipPipPipPipPipPip
  • 21,025 posts
  • LocationNew Orleans, LA

The West is ill-prepared for the wave of “deep fakes” that artificial intelligence could unleash

Russian disinformation has become a problem for European governments. In the last two years, Kremlin-backed campaigns have spread false stories alleging that French President Emmanuel Macron was backed by the “gay lobby,” fabricated a story of a Russian-German girl raped by Arab migrants, and spread a litany of conspiracy theories about the Catalan independence referendum, among other efforts.
Europe is finally taking action. In January, Germany’s Network Enforcement Act came into effect. Designed to limit hate speech and fake news online, the law prompted both France and Spain to consider counterdisinformation legislation of their own. More important, in April the European Union unveiled a new strategy for tackling online disinformation. The EU plan focuses on several sensible responses: promoting media literacy, funding a third-party fact-checking service, and pushing Facebook and others to highlight news from credible media outlets, among others. Although the plan itself stops short of regulation, EU officials have not been shy about hinting that regulation may be forthcoming. Indeed, when Facebook CEO Mark Zuckerberg appeared at an EU hearing this week, lawmakers reminded him of their regulatory power after he appeared to dodge their questions on fake news and extremist content.
 
The problem is that technology advances far more quickly than government policies.

The recent European actions are important first steps. Ultimately, none of the laws or strategies that have been unveiled so far will be enough. The problem is that technology advances far more quickly than government policies. The EU’s measures are still designed to target the disinformation of yesterday rather than that of tomorrow.
To get ahead of the problem, policymakers in Europe and the United States should focus on the coming wave of disruptive technologies. Fueled by advances in artificial intelligence and decentralized computing, the next generation of disinformation promises to be even more sophisticated and difficult to detect.


And remember my friend, future events such as these will affect you in the future.


#64
Yuli Ban

Yuli Ban

    Born Again Singularitarian

  • Moderators
  • PipPipPipPipPipPipPipPipPipPipPip
  • 21,025 posts
  • LocationNew Orleans, LA

A Universal Music Translation Network | Tweaking music compositions to change genres and instruments using machine learning


And remember my friend, future events such as these will affect you in the future.


#65
Yuli Ban

Yuli Ban

    Born Again Singularitarian

  • Moderators
  • PipPipPipPipPipPipPipPipPipPipPip
  • 21,025 posts
  • LocationNew Orleans, LA

Translating instruments, styles, genres at Facebook Artificial Intelligence Research

The AI takes one input, such as a symphony orchestra playing Bach, and translates it into something else, like the same song played on a piano in the style of Beethoven

Is Facebook pumping up the volume on what AI can mean to the future of music? You can decide after having a look at what Facebook AI Research scientists have been up to. A number of sites including The Next Web have reported that they unveiled a neural network capable of translating music from one style, genre, and set of instruments to another.
 
You can check out their paper, "A Universal Music Translation Network" by authors Noam Mor, Lior Wolf, Adam Polyak, Yaniv Taigman, Facebook AI Research.
The paper is on arXiv.
Popular Science, another of the sites showing interest, carried a headline suggesting you might take your bad whistling and make it sound like Mozart.
A video showing the authors' supplementary audio samples lets you hear what they did with samples ranging from symphony, string quartet, to sounds of Africa, Elvis and Rihanna samples and even human whistling.


And remember my friend, future events such as these will affect you in the future.


#66
Yuli Ban

Yuli Ban

    Born Again Singularitarian

  • Moderators
  • PipPipPipPipPipPipPipPipPipPipPip
  • 21,025 posts
  • LocationNew Orleans, LA

Forget DeepFakes, Deep Video Portraits are way better (and worse)

The strange, creepy world of “deepfakes,” videos (often explicit) with the faces of the subjects replaced by those of celebrities, set off alarm bells just about everywhere early this year. And in case you thought that sort of thing had gone away because people found it unethical or unconvincing, the practice is back with the highly convincing “Deep Video Portraits,” which refines and improves the technique.
To be clear, I don’t want to conflate this interesting research with the loathsome practice of putting celebrity faces on adult film star bodies. They’re also totally different implementations of deep learning-based image manipulation. But this application of technology is clearly here to stay and it’s only going to get better — so we had best keep pace with it so we don’t get taken by surprise.
Deep Video Portraits is the title of a paper submitted for consideration this August at SIGGRAPH; it describes an improved technique for reproducing the motions, facial expressions and speech movements of one person using the face of another. Here’s a mild example...

deepvideoportraits.gif


And remember my friend, future events such as these will affect you in the future.


#67
Yuli Ban

Yuli Ban

    Born Again Singularitarian

  • Moderators
  • PipPipPipPipPipPipPipPipPipPipPip
  • 21,025 posts
  • LocationNew Orleans, LA

Using machine learning to turn real people into anime characters

Nijigenka (二次元化) is Japanese for “2D-ification.” It’s a term for when artists take photos of people and turn them into anime characters. But now researchers are starting to have AI do the image-to-image translation. 
At a recent workshop about deep learning in Tokyo, a researcher from Fudan University gave a presentation on creating anime characters with artificial intelligence. Researchers are using deep learning to produce anime versions of real photos. (For more image-to-image translations, watch this clip.)

So... you remember what I said on the second page about how AI couldn't yet distort my face into an anime-styled face? About that...


And remember my friend, future events such as these will affect you in the future.


#68
Yuli Ban

Yuli Ban

    Born Again Singularitarian

  • Moderators
  • PipPipPipPipPipPipPipPipPipPipPip
  • 21,025 posts
  • LocationNew Orleans, LA

DeepMind’s AI can ‘imagine’ a world based on a single picture

DeepMind has developed a neural network that taught itself to ‘imagine’ a scene from different viewpoints, based on just a single image

Artificial intelligence can now put itself in someone else’s shoes. DeepMind has developed a neural network that taught itself to ‘imagine’ a scene from different viewpoints, based on just a single image.
Given a 2D picture of a scene – say, a room with a brick wall, and a brightly coloured sphere and cube on the floor – the neural network can generate a 3D view from a different vantage point, rendering the opposite sides of the objects and altering where shadows fall to maintain the same light source.
The system, called the Generative Query Network (GQN), can tease out details from the static images to guess at spatial relationships, including the camera’s position.

deepmind-object-gif2.gif


And remember my friend, future events such as these will affect you in the future.


#69
Yuli Ban

Yuli Ban

    Born Again Singularitarian

  • Moderators
  • PipPipPipPipPipPipPipPipPipPipPip
  • 21,025 posts
  • LocationNew Orleans, LA

This Nvidia neural network can apply slow motion to any video

Most high-end DSLRs and smartphones can shoot in slow motion, but not all. That’s because doing so is quite data-intensive: Super Slow Motion mode on Sony’s Xperia XZ2 smartphone, for example, shoots 960 frames a second (fps), which is 32 times the amount of frame data it captures at the default 30 fps. That requires a lot of storage, not to mention a processor that’s speedy enough to process every frame.
Nvidia’s novel algorithm, which will be presented at the 2018 Conference on Computer Vision and Pattern Recognition in Salt Lake City this week, can slow down footage after the fact. But unlike the jittery slow motion filters that fill gaps in footage with time-stretched frames, the research team’s solution uses machine learning to hallucinate new frames.


And remember my friend, future events such as these will affect you in the future.


#70
Yuli Ban

Yuli Ban

    Born Again Singularitarian

  • Moderators
  • PipPipPipPipPipPipPipPipPipPipPip
  • 21,025 posts
  • LocationNew Orleans, LA

[SIGGRAPH 2018] Mode-Adaptive Neural Networks for Quadruped Motion Control | AI can now make realistic animal (quadruped) animation cheaply & simply.


And remember my friend, future events such as these will affect you in the future.


#71
Yuli Ban

Yuli Ban

    Born Again Singularitarian

  • Moderators
  • PipPipPipPipPipPipPipPipPipPipPip
  • 21,025 posts
  • LocationNew Orleans, LA

DeepMind's latest attempt at realistic music generation is very impressive yet goes completely unreported by the media.


And remember my friend, future events such as these will affect you in the future.


#72
Yuli Ban

Yuli Ban

    Born Again Singularitarian

  • Moderators
  • PipPipPipPipPipPipPipPipPipPipPip
  • 21,025 posts
  • LocationNew Orleans, LA

Real-time deepfake demo video


And remember my friend, future events such as these will affect you in the future.


#73
Yuli Ban

Yuli Ban

    Born Again Singularitarian

  • Moderators
  • PipPipPipPipPipPipPipPipPipPipPip
  • 21,025 posts
  • LocationNew Orleans, LA

A Robot Walks Into a Bar. But Can It Do Comedy?

It will require a few software leaps, but perhaps within a decade we will begin genuinely laughing at synthetic comedians

One recent evening at a London pub, Piotr Mirowski, 39, stood in front of several dozen comedy fans to prove that an artificially intelligent computer program could perform improvised comedy.
 
In one hand, he held a bug-eyed toy robot, its lines voiced by the program. With the other, he pretended to grip a steering wheel. The robot was playing Mr. Mirowski’s partner; they were taking a scenic drive together.
“I am not trying to be angry,” the robot said, suddenly breaking the mood.
 
“I don’t want you to be angry — this is our quality time,” Mr. Mirowski replied.
 
“I’m sure that you will find love,” the robot said after an awkward pause, drawing a firm end to the couple’s relationship, and prompting laughter from the audience. “I’m so tired,” it added. Mr. Mirowski made a final attempt to save things, but the robot would not listen. “You are not me. You’re my friend,” it said, emotionless.
 
For someone who had just been dumped in front of a paying audience, Mr. Mirowski looked happy. Why? Because the A.I. he created had worked, and stuck to the topic at hand — a rare event, he said later in an interview.


And remember my friend, future events such as these will affect you in the future.


#74
Yuli Ban

Yuli Ban

    Born Again Singularitarian

  • Moderators
  • PipPipPipPipPipPipPipPipPipPipPip
  • 21,025 posts
  • LocationNew Orleans, LA

Style Transfer...For Smoke and Fluids! | Two Minute Papers


And remember my friend, future events such as these will affect you in the future.


#75
Yuli Ban

Yuli Ban

    Born Again Singularitarian

  • Moderators
  • PipPipPipPipPipPipPipPipPipPipPip
  • 21,025 posts
  • LocationNew Orleans, LA

This Online AI Tool Takes Your Words and Turns Them Into Nightmares

We’ve seen lots of machine learning systems create strange new phrases and dreamlike images after being trained on large amounts of data. But a new website lets you do the generating, and the results are just as bizarre as you’d expect. The web applet, built by researcher Cristóbal Valenzuela, is based on a new paper from another team of researchers. Their machine learning algorithm is called AttnGAN, (Attentional Generative Adversarial Network). It’s meant to improve upon other text-to-image AI by refining images at the word level. For now, the results are closer to surrealist art...


And remember my friend, future events such as these will affect you in the future.


#76
Yuli Ban

Yuli Ban

    Born Again Singularitarian

  • Moderators
  • PipPipPipPipPipPipPipPipPipPipPip
  • 21,025 posts
  • LocationNew Orleans, LA

DeepMind's AI Learns The Piano From The Masters of The Past | Take a quick listen and be amazed! Stylistic consistency has been achieved completely by synthesizing waveforms directly rather than playing synthetic instruments


And remember my friend, future events such as these will affect you in the future.


#77
Yuli Ban

Yuli Ban

    Born Again Singularitarian

  • Moderators
  • PipPipPipPipPipPipPipPipPipPipPip
  • 21,025 posts
  • LocationNew Orleans, LA

Bored with your video game? Artificial intelligence could create new levels on the fly

Mario may be super, but even he must get bored hurdling the same Goombas and falling off the same cliffs over and over. Fortunately, a new artificial intelligence (AI) algorithm can endlessly produce new levels, and even tailor them to a player’s skill level.
Computer scientists have spent decades honing “procedural content generation,” the use of algorithms to automatically design new characters, landscapes, and weapons for video games, saving humans hours of labor. (The 2016 game No Man’s Sky can generate up to 18 quintillion unique planets as players explore the galaxy, a daunting task for any human designer.) But programmers still need to handcraft the rules that tell the computer how to create such content. In recent years they’ve applied machine learning, an AI technique by which computers learn from examples, so AI can simply produce more content in the style of existing content without needing explicit instructions. Game levels are particularly tricky to generate, however, because small changes can make them unplayable—a stray wall can seal off a critical passage, for example.  
The new method learns to imitate human-created levels and then allows for customization. It has two phases. In the first, a “generative adversarial network” (GAN) learns through trial and error to transform strings of numbers into levels indistinguishable from human-created levels. A second phase then helps find strings of numbers that lead to levels that are not just realistic, but that fit certain requirements—such as having a lot of enemies or jumps. The authors gained precise control over how difficult the levels were, they report in a paper to be presented in July at the Genetic and Evolutionary Computation Conference in Kyoto, Japan. They believe their approach would work for other games, too.


And remember my friend, future events such as these will affect you in the future.


#78
Yuli Ban

Yuli Ban

    Born Again Singularitarian

  • Moderators
  • PipPipPipPipPipPipPipPipPipPipPip
  • 21,025 posts
  • LocationNew Orleans, LA

This Neural Network Animates Quadrupeds


And remember my friend, future events such as these will affect you in the future.


#79
Yuli Ban

Yuli Ban

    Born Again Singularitarian

  • Moderators
  • PipPipPipPipPipPipPipPipPipPipPip
  • 21,025 posts
  • LocationNew Orleans, LA

AI-Based Video-to-Video Synthesis


And remember my friend, future events such as these will affect you in the future.


#80
Yuli Ban

Yuli Ban

    Born Again Singularitarian

  • Moderators
  • PipPipPipPipPipPipPipPipPipPipPip
  • 21,025 posts
  • LocationNew Orleans, LA

Researchers Come Out With Yet Another Unnerving, New Deepfake Method

This is style transfer, of course: "it also includes examples with blooming flowers, sunrises and sunsets, and clouds and wind."

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.
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.


And remember my friend, future events such as these will affect you in the future.






Also tagged with one or more of these keywords: Artificial intelligence, synthetic media, deepfakes, media synthesis, GANs, artificial imagination, image synthesis, natural language generation, automation, deep learning

0 user(s) are reading this topic

0 members, 0 guests, 0 anonymous users