NIST report warns ‘there is no silver bullet’ for defending against threats to AI systems

The National Institute of Standards and Technology has issued a report explaining how “adversaries can deliberately confuse or even ‘poison’ artificial intelligence systems” and offering mitigation strategies for defenders, along with the stark warning that they may not sufficiently counter such threats.

“The publication, a collaboration among government, academia and industry, is intended to help AI developers and users get a handle on the types of attacks they might expect along with approaches to mitigate them — with the understanding...