English(EN) BadBone: Backdoor Attacks Against Backbone Models in Visual Prompt Learning

新的BadBone攻击针对视觉提示学习模型

作者 PulseAugur 编辑部 · [2 个来源] · 2026-05-29 12:46

研究人员推出BadBone，这是一种针对视觉提示学习模型的新型后门攻击。该攻击会损害骨干模型，导致使用提示学习的下游任务继承漏洞。实验表明BadBone能有效对抗现有防御措施，凸显了该领域新安全措施的必要性。 AI

影响凸显了提示学习中关键的安全漏洞，迫切需要新的防御策略来维护AI模型的完整性。

排序理由该集群包含一篇详细介绍新攻击方法的学术论文。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.CV TIER_1 English(EN) · Ziqing Yang, Rui Wen, Xinlei He, Yun Shen, Michael Backes, Yang Zhang · 2026-06-01 04:00

BadBone：视觉提示学习中骨干模型的后门攻击

arXiv:2605.31246v1 Announce Type: cross Abstract: Prompt learning is a new machine learning paradigm that has attracted ample attention due to its simplicity and proven efficacy. Despite its growing adoption, the security vulnerabilities associated with this paradigm remain under…
arXiv cs.CV TIER_1 English(EN) · Yang Zhang · 2026-05-29 12:46

BadBone：视觉提示学习中骨干模型的后门攻击

Prompt learning is a new machine learning paradigm that has attracted ample attention due to its simplicity and proven efficacy. Despite its growing adoption, the security vulnerabilities associated with this paradigm remain underexplored. In this work, we take the first step to …