Apr 22, 2021

Google launches AI-powered doc services in wide availability

AI
Cloud
Google
Documents
Tilly Kenyon
2 min
Several of Google’s cloud-based, AI-powered doc services have become widely available after being in preview
Several of Google’s cloud-based, AI-powered document services have become widely available after being in preview...

Google has announced that several of its cloud-based, AI-powered document processing products have become generally available after launching in preview last year.

DocAI platform, Lending DocAI, and Procurement DocAI, which have been piloted by thousands of businesses to date, are now open to all customers and include new features and resources.

How do the products work?

Lending DocAI is Google’s first dedicated service for the mortgage industry and it processes mortgage candidates' paperwork. Now in general availability, it also presents a set of specialised AI fashions for paystubs and financial institution statements. The service also now benefits from DocAI platform’s Human-in-the-Loop AI functionality, which supplies a workflow to handle human knowledge evaluate duties.

Human-in-the-Loop AI permits human reviewers to confirm knowledge captured by Lending DocAI, Procurement DocAI, and different choices in DocAI platform. The system exhibits a share rating of how “positive” it is that the AI ingested the doc accurately, and it’s customisable, with the pliability to set totally different thresholds and assign teams of reviewers to levels of a workflow. Builders can select reviewers to assign to duties both from inside their very own firm or from associate organisations.

Procurement DocAI, which performs doc processing for invoices, receipts, and extra, has gained an AI parser for electrical, water, and different utility payments. The newest launch includes Google’s Information Graph to validate data, a system that understands over 500 information about 5 billion entities from the net, in addition to from open and licensed databases. 

All the processors “are created and fine-tuned to achieve industry-leading accuracy, helping businesses confidently unlock insights from documents with machine learning,” Google Cloud product manager Lewis Liu and product marketing manager Yang Liang wrote in a blog post

(Image: Google)

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