Qi, P., Tang, K., Yu, Y., Wu, J., Song, Y., Zhou, W., . . . Yu, N. (2026). VLMShield: Efficient and Robust Defense of Vision-Language Models against Malicious Prompts.
Style de citation Chicago (17e éd.)Qi, Peigui, et al. VLMShield: Efficient and Robust Defense of Vision-Language Models Against Malicious Prompts. 2026.
Style de citation MLA (9e éd.)Qi, Peigui, et al. VLMShield: Efficient and Robust Defense of Vision-Language Models Against Malicious Prompts. 2026.
Attention : ces citations peuvent ne pas être correctes à 100%.