paper-with-me

홈 › Papers

\texttt{Range-Arithmetic}: Verifiable Deep Learning Inference on an Untrusted Party

2025-05-23 · Ali Rahimi, Babak H. Khalaj, Mohammad Ali Maddah-Ali

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.

📄 PDF Abstract BibTeX arXiv:2505.17623

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

SafetyNets: Verifiable Execution of Deep Neural Networks on an Untrusted Cloud

2017-06-30 · NeurIPS 2017 12 · Zahra Ghodsi, Tianyu Gu, Siddharth Garg

Inference using deep neural networks is often outsourced to the cloud since it is a computationally demanding task. However, this raises a fundamental issue of trust. How can a client be sure that the cloud has performed…

speech-recognitionSpeech Recognition

Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware

2018-06-08 · ICLR 2019 5 · Florian Tramèr, Dan Boneh

As Machine Learning (ML) gets applied to security-critical or sensitive domains, there is a growing need for integrity and privacy for outsourced ML computations. A pragmatic solution comes from Trusted Execution Environ…

GPU

VeriLoRA: Fine-Tuning Large Language Models with Verifiable Security via Zero-Knowledge Proofs

2025-08-29 · Guofu Liao, Taotao Wang, Shengli Zhang, Jiqun Zhang 외 arxiv

Fine-tuning large language models (LLMs) is crucial for adapting them to specific tasks, yet it remains computationally demanding and raises concerns about correctness and privacy, particularly in untrusted environments.…

parameter-efficient fine-tuning

LEVIS: Large Exact Verifiable Input Spaces for Neural Networks

2024-08-16 · Mohamad Fares El Hajj Chehade, Brian Wesley Bell, Russell Bent, Hao Zhu 외

The robustness of neural networks is paramount in safety-critical applications. While most current robustness verification methods assess the worst-case output under the assumption that the input space is known, identify…

image-classificationImage ClassificationModel Selection

Efficient and Verifiable Privacy-Preserving Convolutional Computation for CNN Inference with Untrusted Clouds

2025-08-18 · Jinyu Lu, Xinrong Sun, Yunting Tao, Tong Ji 외 arxiv

The widespread adoption of convolutional neural networks (CNNs) in resource-constrained scenarios has driven the development of Machine Learning as a Service (MLaaS) system. However, this approach is susceptible to priva…