Sep 25, 2020

Think in 3D. Create in 3D.

AI
3D design
Amber Naylor
2 min
Expressing ideas in real-time, at any scale.
Expressing ideas in real-time, at any scale...

 

There are debates among designers over the use of 3D content (Virtual Reality VR), compared to 2D designs, using tools such as pen, mouse or screens. The advantages of using a VR headset to create a virtual environment are the speed of manipulations, and the immediate understanding of the proportions in relation to the environment or individuals. Another advantage of using VR to create 3D models is that, now, due to the increasing use of 3D printing, these models created in a virtual world, can be transformed into something of reality design. This transformation process can be completed within a matter of hours, from start to finish. According to designers, the advantages of using VR against traditional 2D design tools screens far outweigh the latter. 

Gravity Sketch is an intuitive 3D design platform for cross-disciplinary teams to create, collaborate, and review in an entirely new way. ” They concept sketched and turn them into reality through the use of 3D models, using a variety of digital technologies within the Virtual Reality field. Gravity Sketch outlines four key advantages to using this modem on creation. 

  • Easy to Use

The design toolset has been built from the foundations up, integrating gestural interaction as its primary input method, resulting in one of the most intuitive design experiences. 

  • Quickly Indeate at Scale 

Speedily communicate and explore ideas using 3D, early within the design process. This will increase the speed of initial development. Solve ergonomic problems in real-time. 

  • Collaborate in Real-Time

Review and create together with colleagues from various locations at the same time, all working within the same digital space. 

  • Communicate Ideas 

To better communicate the design intent, share ideas and work progression in 3D at each stage of the creative process. 

Not only is AI technology reforming the way society functions with smart technologies, but it is also rapidly transforming the way in which these products are firstly created. The impact of this metamorphosis is global, and will rapidly become the new normal for the technology of tomorrow, today. 

Share article

Jun 17, 2021

Facebook Develops AI to Crackdown on Deepfakes

Facebook
MSU
AI
Deepfakes
3 min
Social media giant, Facebook, has developed artificial intelligence that can supposedly identify and reverse-engineer deepfake images

In light of the large tidal wave of increasingly believable deepfake images and videos that have been hitting the feeds of every major social media and news outlet in recent years, global organisations have started to consider the risk factor behind them. While the majority of deepfakes are created purely for amusement, their increasing sophistication is leading to a very simple question: What happens when a deepfake is produced not for amusement, but for malicious intent on a grander scale? 

 

Yesterday, Facebook revealed that it was also concerned by that very question and that it had decided to take a stand against deepfakes. In partnership with Michigan State University, the social media giant presented “a research method of detecting and attributing deepfakes that relies on reverse engineering from a single AI-generated image to the generative model used to produce it.” 

 

The promise is that Facebook’s method will facilitate deepfake detection and tracing in real-world settings, where the deepfake image itself is often the only information detectors have to work with. 

Why Reverse Engineering? 

Right now, researchers identify deepfakes through two primary methods: detection, which distinguishes between real and deepfake images, and image attribution, which identifies whether the image was generated using one of the AI’s training models. But generative photo techniques have advanced in scale and sophistication over the past few years, and the old strategies are no longer sufficient. 

 

First, there are only so many images presented in AI training. If the deepfake was generated by an unknown, alternative model, even artificial intelligence won’t be able to spot it—at least, until now. Reverse engineering, common practice in machine learning (ML), can uncover unique patterns left by the generating model, regardless of whether it was included in the AI’s training set. This helps discover coordinated deepfake attacks or other instances in which multiple deepfakes come from the same source. 

 

How It Works 

Before we could use deep learning to generate images, criminals and other ill-intentioned actors had a limited amount of options. Cameras only had so many tools at their disposal, and most researchers could easily identify certain makes and models. But deep learning has ushered in an age of endless options, and as a result, it’s grown increasingly difficult to identify deepfakes.

 

To counteract this, Facebook ran deepfakes through a fingerprint estimation network (FEN) to estimate some of their details. Fingerprints are essentially patterns left on an image due to manufacturing imperfections, and they help identify where the image came from. By evaluating the fingerprint magnitude, repetition frequency, and symmetrical frequency, Facebook then applied those constraints to predict the model’s hyperparameters. 

 

What are hyperparameters? If you imagine a generative model as a car, hyperparameters are similar to the engine components: certain properties that distinguish your fancy automobile from others on the market. ‘Our reverse engineering technique is somewhat like recognising [the engine] components of a car based on how it sounds’, Facebook explained, ‘even if this is a new car we’ve never heard of before’. 

 

What Did They Find? 

‘On standard benchmarks, we get state-of-the-art results’, said Facebook research lead Tal Hassner. Facebook added that the fingerprint estimation network (FEN) method can be used for not only model parsing, but detection and image attribution. While this research is the first of its kind, making it difficult to assess the results, the future looks promising. 


Facebook’s AI will introduce model parsing for real-world applications, increasing our understanding of deepfake detection. As cybersecurity attacks proliferate, and generative AI falls into the hands of those who would do us harm, this method could help the ‘good guys’ stay one step ahead. As Hassner explained: ‘This is a cat-and-mouse game, and it continues to be a cat-and-mouse game’.

Share article