LRD-MPC: 通过低秩分解实现高效的MPC推断
LRD-MPC: Efficient MPC Inference through Low-rank Decomposition
AI总结：
LRD-MPC通过低秩分解和优化技术，显著提升MPC在深度学习中的推断效率，减少通信开销和计算资源消耗。
摘要：
安全多方计算（MPC）使不信任的各方能够共同计算一个函数而不泄露其输入。其在机器学习（ML）中的应用引起了广泛关注，特别是在跨多个云虚拟机（VM）部署的安全推断服务中，每个VM充当MPC的参与者。模型提供者秘密共享模型权重，用户秘密共享输入，确保每个服务器仅在随机共享上操作。尽管MPC提供强大的加密保证，但其计算和通信开销却相当大。深度神经网络严重依赖卷积和全连接层，这些层在MPC中需要昂贵的矩阵乘法。为了减少这种开销，我们提出利用低秩分解（LRD）来处理线性层，用两个较小的矩阵乘法代替一个大的矩阵乘法。每个MPC中的矩阵乘法都会带来一轮通信，这意味着将一个矩阵乘法分解成两个会导致额外的通信轮次。其次，额外的矩阵乘法需要额外的截断步骤以保持数值精度。由于截断本身需要通信和计算，这些开销可能会抵消分解带来的收益。为了解决这个问题，我们引入了两种互补的优化：截断跳过和高效的线性层连接。截断跳过消除了由LRD引起的额外截断，而线性层连接将操作流水线化以隐藏额外的通信轮次。共同，这些技术减轻了LRD在MPC中的主要开销并提高了整体效率。我们的方法在MPC协议中具有广泛的应用性。实验显示，与全秩基线相比，在n-PC和3-PC协议中分别达到了25%和33%的速度提升，同时实现了高达52%的GPU能耗节省和88%的离线阶段延迟减少。
英文摘要：
Secure Multi-party Computation (MPC) enables untrusted parties to jointly compute a function without revealing their inputs. Its application to machine learning (ML) has gained significant attention, particularly for secure inference services deployed across multiple cloud virtual machines (VMs), where each VM acts as an MPC party. Model providers secret-share model weights, and users secret-share inputs, ensuring that each server operates only on random shares. While MPC provides strong cryptographic guarantees, it incurs substantial computational and communication overhead. Deep neural networks rely heavily on convolutional and fully connected layers, which require costly matrix multiplications in MPC. To reduce this cost, we propose leveraging low-rank decomposition (LRD) for linear layers, replacing one large matrix multiplication with two smaller ones. Each matrix multiplication in MPC incurs a round of communication, meaning decomposing one matrix multiplication into two leads to an additional communication round. Second, the added matrix multiplication requires an additional truncation step to maintain numerical precision. Since truncation itself requires communication and computation, these overheads can offset the gains from decomposition. To address this, we introduce two complementary optimizations: truncation skipping and efficient linear layer concatenation. Truncation skipping removes the extra truncation induced by LRD, while linear layer concatenation pipelines operations to hide the additional communication round. Together, these techniques mitigate the main overheads of LRD in MPC and improve overall efficiency. Our approach is broadly applicable across MPC protocols. Experiments show up to 25% speedup in n-PC and 33% in 3-PC protocols over full-rank baselines, along with up to 52% GPU energy savings and 88% reduction in offline-phase latency.
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。
