Hello, Guest!

Nand Mulchandani on JAIC’s Efforts to Counter Adversarial AI

1 min read

Nand Mulchandani, chief technology officer of the Department of Defense’s (DoD) Joint Artificial Intelligence Center (JAIC), said JAIC is working on new approaches on how model and data sharing could come up with a manifest that helps counter cyber attacks that try to hinder or confuse algorithms when it comes to releasing sensitive data, FedScoop reported Thursday. 

“The trick is to figure out what tech/products are ready to deploy and in what ‘domain,'” Mulchandani told the publication. “We think that AI explainability, AI security, AI ethics, and AI testing are all tightly connected and have very tight collaboration between the various groups that are tackling these areas."

He said JAIC considers data used to train these AI algorithms as its most important intellectual property in need of protection against cyber vulnerabilities. 

Cheryl Ingstad, director of the Department of Energy's (DoE) Artificial Intelligence & Technology Office, announced the possibility of a tool that examines AI algorithms for bias. The tool would enforce ethical principles as well as cyber hygiene.

“Adversarial AI is an area where we need to do a lot of innovation around it and create new principles and new processes and methodologies to address it,” Ingstad said.