提出可验证的深度神经网络推理框架，提升计算效率与安全性。
\texttt{Range-Arithmetic}: Verifiable Deep Learning Inference on an Untrusted Party
- 将非算术操作转为可验证的算术步骤，利用求和校验与范围证明
- 验证开销、计算成本和通信量均低于现有方法
- 适合区块链环境下的可信外包推理，兼容有限域证明系统
可验证计算（VC）在去中心化机器学习系统中日益重要，因区块链限制需将资源密集型任务如深度神经网络（DNN）推理外包给外部参与者。这要求在不重新执行的情况下验证外包计算的正确性。本文提出 exttt{Range-Arithmetic} 框架，实现高效且可验证的 DNN 推理，将非算术操作（如定点矩阵乘法后的舍入、ReLU）转化为可通过求和校验协议与拼接范围证明验证的算术步骤。该方法避免了布尔编码的复杂性、高次多项式及大型查找表，同时兼容基于有限域的证明系统。实验表明，本方法在性能上达到现有水平，且显著降低结果验证的计算成本、执行方的计算负担以及双方间的通信开销。
原文摘要 · Abstract (English)
Verifiable computing (VC) has gained prominence in decentralized machine learning systems, where resource-intensive tasks like deep neural network (DNN) inference are offloaded to external participants due to blockchain limitations. This creates a need to verify the correctness of outsourced computations without re-execution. We propose \texttt{Range-Arithmetic}, a novel framework for efficient and verifiable DNN inference that transforms non-arithmetic operations, such as rounding after fixed-point matrix multiplication and ReLU, into arithmetic steps verifiable using sum-check protocols and concatenated range proofs. Our approach avoids the complexity of Boolean encoding, high-degree polynomials, and large lookup tables while remaining compatible with finite-field-based proof systems. Experimental results show that our method not only matches the performance of existing approaches, but also reduces the computational cost of verifying the results, the computational effort required from the untrusted party performing the DNN inference, and the communication overhead between the two sides.
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。