attack-attention

有效攻击基础模型的注意力可有效扰乱下游任务 论文 "Attacking Attention of Foundation Models Effectively Disrupts Downstream Tasks" 的官方 PyTorch 实现，已被 CVPR 2025 的 ADVML （对抗性机器学习在计算机视觉中的应用：基础模型 + X）研讨会接收。 有效攻击基础模型的注意力可有效扰乱下游任务" Hondamunige Prasanna Silva、Federico Becattini 和 Lorenzo Seidenari 摘要：...

Attacking Attention of Foundation Models Disrupts Downstream Tasks

Foundation models represent the most prominent and recent paradigm shift in artificial intelligence. Foundation models are large models, trained on broad data that deliver high accuracy in many downstream tasks, often without fine-tuning. For this reason, models such as CLIP , DINO or Vision...