用差分隐私保护数据存储，让设备端检索增强模型安全共享数据。
Differentially Private Datastore Generation for Retrieval-Augmented Inference
- 基于局部敏感哈希分桶，加噪声生成类别概率分布。
- 在ε=5下平均准确率仅降2.6%，隐私保护效果强。
- 适用于各类安全数据存储场景，抵御成员推理攻击。
现代设备端基于检索的AI系统需在不泄露个体隐私的前提下共享数据存储。本文提出一种基于哈希的概率生成框架，通过局部敏感哈希（LSH）将高维数据高效分桶，并对每桶累积投票添加校准的差分隐私（DP）噪声，生成类别概率分布。该方法适用于任意需要安全键值存储创建与发布的流程。我们在七个数据集上进行实验，样本量和类别数分别为2至14。在ε=5时，释放的DP数据存储实现强隐私保护，平均准确率仅下降2.6%。此外，针对成员推理攻击的基准测试显示，攻击准确率降至53.60%。
原文摘要 · Abstract (English)
It is crucial for modern on-device AI systems that rely on retrieval-augmented inference to release and share datastores without compromising individual privacy. This can be achieved using Differential Privacy (DP), which provides a formal guarantee that ensures individual contributions remain indistinguishable, even under adversarial analysis. In this paper, we introduce a hashing-based probability generation framework designed to enable the creation and release of differentially private datastores. Our approach employs locality-sensitive hashing (LSH) to efficiently partition high-dimensional data into buckets. We then add calibrated DP noise to the accumulated vote for each bucket, generating a probability distribution across classes. Our method is broadly applicable to any pipeline requiring secure key,value datastore creation and release. We conducted experiments on seven datasets with varying sample sizes and class counts, ranging from 2 to 14. At epsilon=5, our released DP datastore achieves strong privacy protection with only an average 2.6% drop in accuracy. Finally, we benchmark DP datastore resilience to membership inference attacks, reducing attack accuracy to 53.60%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。