← All news

Artificial Intelligence

Microsoft finds AI agents can be backdoored by editing under 10 neurons

Some neurons in large language models are rarely activated. Microsoft researchers have found a way to turn fewer than 10 of these dormant neurons into a hidden backdoor, making an otherwise normal AI model behave as expected until it encounters a specific trigger.

Read the full story on The Next Web.

Read at source (opens in a new tab)

Latest from The Next Web