arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.02522cs.CRcs.AI
收藏

Opal:面向个人AI的隐私内存

Opal: Private Memory for Personal AI

Google DeepMind(谷歌DeepMind);UC Berkeley(加州大学伯克利分校)

Darya Kaviani, Alp Eren Ozdarendeli, Jinhao Zhu, Yu Ding, Raluca Ada Popa

AI总结:

Opal通过将数据依赖推理与个人数据分离,利用可信 enclave 提高检索准确率,并在基础设施成本上取得显著优势。

摘要:

个人AI系统越来越多地保留用户活动的长期记忆,包括文档、电子邮件、消息、会议和环境录音。可信硬件可以保持这些数据的隐私,但难以扩展到增长的数据存储。这迫使数据存储到外部存储,从而暴露了检索访问模式,泄露了隐私信息给应用提供者。Oblivious RAM (ORAM) 是一种加密原语,可以隐藏这些模式,但需要固定的访问预算,阻碍了代理记忆系统依赖的查询依赖性遍历。我们提出了Opal,一种面向个人AI的隐私内存系统。我们的关键见解是将所有数据依赖的推理与大量个人数据分离,将其限制在可信 enclave 内。不受信任的磁盘只看到固定、无偏见的内存访问。此 enclave 居住组件使用轻量级知识图谱来捕捉个人情境,语义搜索单独遗漏的,并通过在每次 ORAM 访问上利用重新索引和容量管理来处理连续摄入。在由随机通信模型驱动的全面合成个人数据管道上进行评估,Opal 在语义搜索基础上将检索准确率提高13个百分点,并在基础设施成本低15倍的情况下,达到29倍的吞吐量。Opal正考虑部署到数百万用户,由一家主要AI提供商考虑。

英文摘要:

Personal AI systems increasingly retain long-term memory of user activity, including documents, emails, messages, meetings, and ambient recordings. Trusted hardware can keep this data private, but struggles to scale with a growing datastore. This pushes the data to external storage, which exposes retrieval access patterns that leak private information to the application provider. Oblivious RAM (ORAM) is a cryptographic primitive that can hide these patterns, but it requires a fixed access budget, precluding the query-dependent traversals that agentic memory systems rely on for accuracy. We present Opal, a private memory system for personal AI. Our key insight is to decouple all data-dependent reasoning from the bulk of personal data, confining it to the trusted enclave. Untrusted disk then sees only fixed, oblivious memory accesses. This enclave-resident component uses a lightweight knowledge graph to capture personal context that semantic search alone misses and handles continuous ingestion by piggybacking reindexing and capacity management on every ORAM access. Evaluated on a comprehensive synthetic personal-data pipeline driven by stochastic communication models, Opal improves retrieval accuracy by 13 percentage points over semantic search and achieves 29x higher throughput with 15x lower infrastructure cost than a secure baseline. Opal is under consideration for deployment to millions of users at a major AI provider.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑