DefendAI: Army wants industry help with safety testing for artificial intelligence
The Army presented a conceptual security plan that involves layers of security for AI use, but wants help ironing out the details.
Stay updated with breaking news from Project Linchpin. Get real-time updates on events, politics, business, and more. Visit us for reliable news and exclusive interviews.
The Army presented a conceptual security plan that involves layers of security for AI use, but wants help ironing out the details.
Launched in March, the effort is looking at poisoned datasets, adversarial attacks, Trojans, and more.
“Any commercial LLM that is out there, that is learning from the internet, is poisoned today,” Jennifer Swanson said, “but our main concern [is] those algorithms that are going to be informing battlefield decisions.”
The service is also currently developing a risk management framework for Project Linchpin, the Army’s first program of record to help build out a trusted artificial intelligence/machine learning pipeline, according to Jen Swanson, deputy assistant secretary of the Army for data, engineering and software.
Here's what to watch for in the defense network, cyber and innovation space in 2024.