实现神经网络推理的端到端匿名，保护用户隐私
Towards Anonymous Neural Network Inference
- 通过存储-计算-存储模式隐藏通信与计算特征
- 量化执行时间至公开延迟桶，抵御时序分析攻击
- 兼容生产级负载，适合关注隐私的云服务用户
我们提出 funion，一个提供神经网络推理中发送方与接收方完全不可链接性的系统。该系统基于鸽巢存储协议与 Echomix 中的 BACAP（盲化与能力）机制，继承现代混洗网的安全保障。用户可将输入张量匿名存入伪随机存储位置，委托计算服务通过神经网络处理，并以无痕迹方式获取结果。该存储-计算-存储范式同时掩盖网络流量模式与计算负载特征，将执行时间量化为公开延迟桶。安全分析表明，在与 Echomix 相近的信任假设下，funion 能保持强元数据隐私，且对生产规模工作负载引入可接受开销。本工作为用户提供了一个可访问的平台，可向云服务提交完全匿名的推理请求。
原文摘要 · Abstract (English)
We introduce funion, a system providing end-to-end sender-receiver unlinkability for neural network inference. By leveraging the Pigeonhole storage protocol and BACAP (blinding-and-capability) scheme from the Echomix anonymity system, funion inherits the provable security guarantees of modern mixnets. Users can anonymously store input tensors in pseudorandom storage locations, commission compute services to process them via the neural network, and retrieve results with no traceable connection between input and output parties. This store-compute-store paradigm masks both network traffic patterns and computational workload characteristics, while quantizing execution timing into public latency buckets. Our security analysis demonstrates that funion inherits the strong metadata privacy guarantees of Echomix under largely the same trust assumptions, while introducing acceptable overhead for production-scale workloads. Our work paves the way towards an accessible platform where users can submit fully anonymized inference queries to cloud services.
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。