Jun 9, 2021

IBM announce Uncertainty Quantification 360 toolkit

2 min
IBM has released Uncertainty Quantification 360, which gives AI the ability to express if it is unsure, adding transparency for the safe deployment of AI

IBM has created the Uncertainty Quantification 360 toolkit and made it available to the open-source community. Released at the 2021 IBM Data & AI Digital Developer Conference, Uncertainty Quantification 360 (UQ360) is aimed at giving data scientists and developers algorithms to streamline quantifying, evaluating, improving and communicating uncertainty of machine learning models.

The UQ toolkit is designed to boost the safety of AI models by giving them the “intellectual humility” they need to use when they’re unsure of something. It’s a collection of algorithms that can be used to quantify an AI model’s uncertainty. It also provides capabilities to measure and improve uncertainty quantification to streamline development processes, as well as taxonomy and guidance to help developers choose which capabilities are appropriate for specific models.

IBM research staff members Prasanna Sattigeri and Q. Vera Liao explained in a blog post, that the choice of UQ method depends on a number of factors, including the underlying model, the type of machine learning task, characteristics of the data, and the user’s goal. Sometimes a chosen UQ method might not produce high-quality uncertainty estimates and could mislead users, so it’s crucial for developers to evaluate the quality of UQ and improve the quantification quality if necessary before deploying an AI system.

UQ360 can improve different kinds of AI

Sattigeri and Liao said UQ 360 can be used to improve hundreds of different kinds of AI models where safety is a paramount concern, an example they provide is AI that’s used to diagnose medical issues such as sepsis.

“Early detection of sepsis is important and AI can help, but only when predictions are accompanied by meaningful uncertainty estimates,” Sattigeri and Liao explained. “Only then can doctors immediately treat patients AI has confidently flagged as at-risk and prescribe additional diagnostics for those AI has expressed a low level of certainty about. If the model produces unreliable uncertainty estimates, patients may die.”

The researchers suggest that knowing the margin of error might also be useful for real estate agents who use AI-based house price prediction models, or for models that try to predict the impact of new product features.

“For every UQ algorithm provided in the UQ360 Python package, a user can make a choice of an appropriate style of communication by following our psychology-based guidance on communicating UQ estimates, from concise descriptions to detailed visualisations,” the researchers explained.

The UQ 360 toolkit is available to download now, and IBM is asking the community to contribute to its development going forward to ensure that AI practitioners can understand and communicate the limitations of their algorithms.


Share article

Jun 17, 2021

Facebook Develops AI to Crackdown on 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