1
Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs
提出频域正则化对抗对齐方法，提升对闭源多模态大模型的迁移攻击成功率，是AI安全领域的重要进展。
arXiv:2605.21541v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) remain vulnerable to transfer-based targeted attacks, where…