\texttt{Range-Arithmetic}: Verifiable Deep Learning Inference on an Untrusted Party
This addresses the need for efficient verifiable computing in decentralized machine learning systems where inference is offloaded to external participants.
The paper tackles the problem of verifying deep neural network inference computations performed by untrusted parties in decentralized systems, proposing Range-Arithmetic to transform non-arithmetic operations into verifiable arithmetic steps. The method reduces computational costs for verification and untrusted parties while maintaining performance comparable to existing approaches.
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.