Imperio
Public[IJCAI 2024] Imperio is an LLM-powered backdoor attack. It allows the adversary to issue language-guided instructions to control the victim model's prediction for arbitrary targets.
Creat:2024-01-02T16:13:03
Update:2025-02-18T09:51:48
https://khchow.com/Imperio/
42
Stars
0
Stars Increase