Jan 22, 2021

Bear Flag Robotics raises $7.9mn for autonomous tractors

Agtech
agriculture
Bear Flag Robotics
AI
William Smith
2 min
Bear Flag Robotics is developing autonomous tractors for use on farms, offering a software package allowing remote monitoring and command capabilities
Bear Flag Robotics is developing autonomous tractors for use on farms, offering a software package allowing remote monitoring and command capabilities...

Newark, California-based Bear Flag Robotics is developing autonomous tractors for use on farms.

Citing the fact that “transportation incidents”, which include tractor overturns, are the leading cause of death for farm workers, the company provides technology and services to run tractors autonomously. It works with produce and commodity flowers in California and Arizona, offering a software package allowing remote monitoring and command capabilities, as well as analytics to improve processes.

Significant backing

Since its 2017 foundation, the company has raised $12.5mn across five funding rounds. Its latest seed round alone saw Bear Flag Robotics raise $7.9mn from lead investors True Ventures, alongside Green Cow Venture Capital, Graphene Ventures, D20 Capital and AgFunder.

In a press release, AgFunder partner Rob Leclerc said: "I absolutely love this team and their mission, but when their customers told us how much they loved their Bear Flag tractors, and how farmers from the region would see it in the field and come pay a visit, we knew that this was a special company. Bear Flag has the potential to be one of the most important companies in agriculture over the next decade."

Automation the solution?

The company identified a number of challenges facing the industry, with the farm labour pool diminishing and climate change forcing growing seasons into shorter periods, that automation has the potential to resolve.

"When we first invested in [the company], we saw an innovative, passionate team bringing automation to farms," said Rohit Sharma, partner at True Ventures. "The impact of what Bear Flag Robotics delivers is meaningful every single day for farm operations, growers and consumers."

The agriculture tech industry has seen a number of developments in recent years, whether that’s using drones to improve the farming of hazelnuts or robotic, autonomous greenhouses that use hydroponics to maximise the space to yield ratio of robot-planted crops. 

(Image: Bear Flag Robotics)

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