AEWIN and UNISEM partner to launch Edge AI solutions
AEWIN, which provide smartly designed networking platforms, announces partnership with UNISEM to accelerate the move into the AI-assisted future. UNISEM has taken its video analytics expertise and implemented it into useful real-world applications.
UNISEM developed a solution that is based on AI’s Deep Learning method to help in solving traffic problems caused by complex and diverse traffic environment, and drivers’ traffic law disobedience. UniTraffic is a traffic management technology that utilises deep learning-based image processing technology and multi-object detection that counts and classifies on-road objects such as pedestrians, automobiles, motorcycles, and trucks. It can also detect the licence plate number of vehicles that violated traffic regulations.
According to the company, it has 99% accuracy for multiple object recognition in real-time. UniTraffic solution provides statistics and traffic flow patterns to plan future infrastructural development and upgrades. Likewise, for city administration and police departments, UniTraffic can minimise the time used for administering tickets and reduce personnel costs.
“UNISEM’s vision aligned closely with AEWIN’s hardware development roadmap. The continued relationship allowed us the integrate designs optimal for UNISEM’s specific hardware requirements,” said Charles Lin, CEO at AEWIN. “Today’s announcement is the result of the past few years of cooperation. Through repeated testing and benchmarking, AEWIN has thoroughly investigated the performance characteristics of the UNISEM software suite that allows us to provide a workload-optimised total solution.”
UniSafety can help prevent incidents during manufacturing
To prevent various accidents during the manufacturing process, AEWIN cooperates with UNISEM’s IoT Division to provide UniSafety, an AI-based computer vision solution. This is a Smart Factory solution that uses Deep Learning-based computer vision technology to provide a safe work environment, prevent potential accident, and reduce serious injuries.
UniSafety is based on video analytics technology enhanced with deep learning that allows detection of various dangerous situations, such as fire, falling materials, non-wearing of safety equipment, intrusion, etc., that can occur during the production process. In the case of an accident or unusual situation, the system informs the safety supervisors via web-dashboard notification, text message, and loudspeaker. It also offers motion detection for detecting unauthorised access or intrusions.
“AEWIN has been exceedingly helpful in our quest to find the right hardware to host our solutions. AEWIN has not only provided insights in hardware design and selection, as well as taking our software in-house to provide customised firmware specific for our workloads,” said Jung Boo Eun, the Managing Director from UNISEM.
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’.