Wang, H., & Shu, K. (2023). Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment.
Style de citation Chicago (17e éd.)Wang, Haoran, et Kai Shu. Trojan Activation Attack: Red-Teaming Large Language Models Using Activation Steering for Safety-Alignment. 2023.
Style de citation MLA (9e éd.)Wang, Haoran, et Kai Shu. Trojan Activation Attack: Red-Teaming Large Language Models Using Activation Steering for Safety-Alignment. 2023.
Attention : ces citations peuvent ne pas être correctes à 100%.