Microsoft finds AI agents can be backdoored by editing under 10 neurons
· thenextweb.com · popularity 21/100 · 0 similar stories today · AI & Data Science (Artificial Intelligence)
Read the original at thenextweb.com →
Summary
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. Once activated, the model can execute malicious commands. The technique, called Lazarus, […] This story continues at The Next Web
Found in: The Next Web. Rating basis: single outlet; outlet tier 2 (unlisted); 1 feeds; feed position 2.