TSA seeks smarter luggage scanners

The Transportation Security Administration wants high-tech start-ups to fuel development of smarter, faster detection capabilities for airport luggage scanners.

Shutterstock ID 705220987 By Phonlamai Photo
 

The Transportation Security Administration is tapping into alternative contracting techniques and Silicon Valley startups to accelerate development of rapidly adaptive screening capabilities for its airport detection systems.

TSA's Office of Requirements and Capabilities Analysis said it was working with the Department of Homeland Security's Science & Technology Directorate on an Other Transaction Solicitation for a new way to detect evolving threats carried in airline passenger luggage.

"This solicitation allows us to create a partnership between TSA and the nation’s innovators to develop revolutionary technology solutions to keep this country and our people safe," acting S&T Undersecretary William N. Bryan said in a May 2 statement.

TSA is looking  to develop software and capabilities with startup tech companies that could be easily plugged into detection gear at airports to identify subtle, but potentially devastating, threats to aircraft that might get past current airport baggage scanners, according to its solicitation.

The security agency wants to move away from expensive and proprietary detection capabilities in its luggage screening hardware, while also avoiding labor-intensive hand searches. Instead, the solicitation suggests, an image library combined with artificial intelligence could to learn to identify new items and distinguish between benign objects and potential threats.

Rapidly changing consumer electronics, it said, are an example of a dynamic  threat vector that evolves faster than next-generation detector hardware. TSA personnel looking at baggage scanner images might miss subtle new differences in how newly introduced consumer devices are wired or put together.

The agency wants developers to come up with AI-based methods that could automate detection algorithm training, allowing detection hardware to "intuitively recognize" such subtleties and new objects that come through airports in luggage.

The OTS would fund development efforts in four three- to six-month $200,000 sprints. TSA is holding an industry day in Menlo Park, Calif.,  on May 4.