We have developed multiple AIs that identify threats. These cover both detection in images or in data streams.
New methods have been used to detect anomalies. The emergence of auto-encoders to learn what “normal” looks like and then raise alerts when “abnormal” patterns are detected are transforming the capability.
This approach overcomes the issues with traditional methods requiring examples of issues to learn. We can now see ways to keep pace with emerging threats as well as those we have seen before.
Use case: X-ray Threat Detection

X-Ray Images

Support Officer Assessment of X-Ray Images at Airport Security

  • Aurora-AI has developed a solution that has been trained to spot guns, knives and bombs in x-ray images captured at the airport security checkpoint.
  • Supporting an officer to highlight images where suspect patterns have been detected offers the prospect of improving security and throughput.

MM Wave Images

Detect Threats Using Remote Sensing

  • We have worked with images captured using passive emissions to enable automated detection of threat objects.
  • This demonstrates the ability to manage security without people having to be still or remove outer layers of clothing, improving passenger experience.

Network Intrusion

Detect Unexpected Network Traffic

  • Our proof of concept AI “learnt” standard profiles of network traffic raising alerts when abnormal data packets were detected.
  • The solution could be setup to perform continuous learning to ensure improvement over time with reducing levels of false alarm.