English(EN) Forget What's Sensitive, Remember What Matters: Token-Level Differential Privacy in Memory Sculpting for Continual Learning

新框架平衡持续学习中的隐私和效用

作者 PulseAugur 编辑部 · [1 个来源] · 2026-05-25 04:00

研究人员开发了一种用于持续学习模型的新型框架，旨在增强隐私。这种新方法 PeCL 根据单个数据令牌的语义敏感性自适应地分配差分隐私预算。它旨在保护敏感信息，同时保留通用知识以防止灾难性遗忘。实验表明，与传统方法相比，PeCL 在隐私和模型效用之间取得了更好的平衡。 AI

影响引入了一种更细致的持续学习隐私方法，有可能在敏感领域实现更广泛的部署。

排序理由该集群包含一篇学术论文，详细介绍了具有差分隐私的持续学习的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

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; 该集群包含一篇学术论文，详细介绍了具有差分隐私的持续学习的新方法。[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: 136 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。

arXiv cs.AI TIER_1 English(EN) · Bihao Zhan, Jie Zhou, Junsong Li, Yutao Yang, Shilian Chen, Qianjun Pan, Xin Li, Wen Wu, Xingjiao Wu, Qin Chen, Hang Yan, Liang He · 2026-05-25 04:00

忘掉敏感信息，记住重要内容：持续学习记忆塑形中的令牌级差分隐私

arXiv:2509.12958v2 Announce Type: replace Abstract: Continual Learning (CL) models, while adept at sequential knowledge acquisition, face significant and often overlooked privacy challenges due to accumulating diverse information. Traditional privacy methods, like a uniform Diffe…