ACLMay, 2024
SpeechGuard: 多模态大型语言模型的对抗鲁棒性探索
SpeechGuard: Exploring the Adversarial Robustness of Multimodal Large Language Models
Raghuveer Peri, Sai Muralidhar Jayanthi, Srikanth Ronanki, Anshu Bhatia, Karel Mundnich...
TL;DR通过设计算法进行白盒和黑盒攻击以实现越狱,提出了对抗越狱攻击的对策,并展示了该对策显著降低攻击成功率。