Researchers demo AI-crippling GPUHammer attack

Researchers demo AI-crippling GPUHammer attack
News Technology Security Researchers demo AI-crippling GPUHammer attack Nvidia confirms serious Rowhammer style memory vulnerability. Security researchers have successfully demonstrated the first Rowhammer attack targeting graphics processing unit (GPU) memory, revealing a critical vulnerability that could allow attackers to sabotage artificial intelligence models running on widely used Nvidiahardware. The attack, dubbed GPUHammer, was developed by researchers Chris Lin, Joyce Qu and Gururaj Sai...

Save to Folder

Choose a folder to save this article: