English(EN) SPACE: Source-free Proxy Anchor Concept Erasure for MLLMs

新的SPACE框架实现了多模态大语言模型的无源模型遗忘

作者 PulseAugur 编辑部 · [1 个来源] · 2026-06-10 04:00

研究人员推出了一种新颖的框架SPACE，用于多模态大语言模型（MLLMs）的无源模型遗忘。该方法允许在不直接访问目标概念的情况下移除敏感数据，解决了隐私和监管问题。SPACE利用文本引导的代理锚点和双约束语义隔离，间接擦除概念，同时保持模型的整体性能和结构完整性。实验表明，SPACE取得的结果与现有的依赖数据的方法相当。 AI

影响为多模态AI系统提供了更强大的隐私控制，可能有助于简化监管合规。

排序理由这是一篇描述一种新的模型遗忘方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

MLLMs

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一篇描述一种新的模型遗忘方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 91 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Zhijing Zhang, Jiaqi Ding, Qianshan Wei, Nan Zhou, Jiaqi Li, Yongliang Wu, Tongxin Zhu, Xiaolin Fang · 2026-06-10 04:00

SPACE：MLLMs 的无源代理锚点概念擦除

arXiv:2606.09868v1 Announce Type: cross Abstract: As Multimodal Large Language Models (MLLMs) face growing privacy risks and regulatory constraints, machine unlearning (MU) has emerged as a crucial solution for removing sensitive data while preserving model performance. However, …

本文如何被排名

报道来源 [1]

SPACE：MLLMs 的无源代理锚点概念擦除

相关实体

相关话题