Synadel

VTT LaunchPad spin-off incubator team

Synadel addresses a critical bottleneck in defence and security: the lack of real-world data needed to train machine learning algorithms. With Synadel’s ability to create synthetic data, the time it takes the airport security inspection devices to detect new threats is reduced from months to days.

The problem

In today’s globally challenging security landscape, organizations’ ability to quickly respond to new threats is constantly contested. Failure to respond timely can ultimately lead to a loss of lives, and even in less severe cases, financial damage can be extremely high. Machine learning algorithms, such as automatic threat detection in airport security inspection, are essential to tackling these issues.

Whenever a new threat is identified, the automatic threat detection algorithms need to be retrained. However, in the case of airport security devices, the current retraining process requires collecting vast amounts of training data by scanning real luggage and individuals. Such a method is

  • labor-intensive
  • slow, up to several months
  • burdened with data privacy and security issues.

The gap between identifying a threat and updating algorithms creates notable security vulnerabilities.

 

Our solution

To address this problem, Synadel will bring to market a groundbreaking prototype developed and tested in collaboration with key aviation security stakeholders.  

Our solution generates synthetic data that is identical to the real data produced by current airport security devices. Synthetic data sets created with our solution are automatically annotated and can feature any new threat object and material. With our solution, data needed to train automatic threat detection algorithms can be created as soon as a threat is identified. There is no longer a need to scan real luggage or individuals.

At the core of the solution is a physics-based simulation of complex X-ray and mmWave radar signal interactions with virtual materials processed as a computer graphics problem combined with generative AI. With this approach, data identical to the X-ray Computer Tomography and mmWave person scanning devices can be created efficiently. 

The development of this solution has been enabled by years of research at VTT and our team's unique background on computer graphics, simulation, machine learning and physics behind the security inspection devices.

 

Our vision

Synadel will improve aviation security by helping the ecosystem stakeholders respond to new threats faster. 

In the long run, the aim is to extend the synthetic data offering enabled by our solution to cases outside aviation security. With our core technology, a vast number of synthetic data needs in the defense and security field can be addressed. 

Our goal is to grow Synadel to be the main synthetic data provider in the defense and security field in the next 5 years. 

Share
LaunchPad logo
VTT LaunchPad

The science-based incubator VTT LaunchPad delivers VTT’s strategy to renew industries and society by spinning off companies built on VTT’s technologies. In the incubator, we bring VTT researchers and IPR together with the best business minds and investors out there.

[email protected]

Read more about Launchpad