BlackBerry outs Persona ‘continuous authentication’ AI tool
Built on the BlackBerry Spark platform, the company claims Persona Desktop is the first cybersecurity solution to leverage biometric and behaviour-based machine learning models to create a real-time trust score for laptop and desktop users.
It aims to protect employees whose logins have been stolen, protect companies against rogue employees and protect staff and organisations against compromised software.
Persona continually monitors behaviour and device interaction, creating a user profile and taking action when usage patterns deviate from the norm. The software can then prompt for further authentication or disable access to a device.
Frank Cotter, senior vice president of product management at BlackBerry, said, “For organisations that are adopting a zero trust model, BlackBerry Persona removes the friction of unnecessary re-authentication by continuously verifying a user’s identity after log-in. With continuous authentication, BlackBerry Persona uses behaviour analysis to recognise software usage patterns and determine what behaviour is high or low risk in real time. We are committed to developing innovative ways to keep our customers safe and secure and are proud to be the first to bring a solution like Persona Desktop to market.”
"Building authentication into the endpoint places a strong cybersecurity control at a critical control point; it’s a no brainer!”
Frank Dickson, program vice president of cybersecurity products at IDC, said, “It has long been a puzzle why we place sophisticated endpoint security platforms on devices but allowed a simple username and password to easily bypass that protection. We have long advocated for embedded user authentication while not impacting user experience, applying modern technology to continually validate a user. Building authentication into the endpoint places a strong cybersecurity control at a critical control point; it’s a no brainer!”
Nigel Thompson, VP product marketing at BlackBerry, told Technology Magazine, “BlackBerry Persona is built to deliver AI-driven continuous authentication and behaviour analytic solution that is able to identify suspicious users in real-time to prevent security breaches.” Asked if the technology could be fooled by erratic user behaviour, he said, “No. Erratic user behaviour would simply trigger a secondary action such as a two factor authentication request.”
BlackBerry Persona Desktop is available as part of BlackBerry Cyber Suite.
Facebook Develops AI to Crackdown on Deepfakes
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’.